Publish AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,184 @@
+---
+license: apache-2.0
+library_name: mlx
+base_model: Qwen/Qwen3-VL-32B-Thinking
+base_model_relation: quantized
+pipeline_tag: image-text-to-text
+tags:
+- mlx
+- apple-silicon
+- quantized
+- mixed-precision
+- axquant
+- axq
+- development
+- qwen3-vl
+- 6bit
+- 6-bit
+- vision
+---
+
+# AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit — 6.94 BPW measured main
+
+An **AXQuant (AXQ)** mixed-precision MLX checkpoint for Apple Silicon, converted directly from
+the BF16 source model. The language path is quantized while the vision tower are preserved at BF16 in the checkpoint (or a bound sidecar when present).
+
+> **Development evidence — not a certified AXQuant release.** This package has conversion and
+> artifact-integrity records, but it does not publish measured quality, long-context, kernel-speed,
+> or MTP-speed evidence. Do not interpret the AXQ product label as a benchmark claim.
+
+
+## Model details
+
+| Property | Value |
+| --- | --- |
+| Base model | [Qwen/Qwen3-VL-32B-Thinking](https://huggingface.co/Qwen/Qwen3-VL-32B-Thinking/tree/7edd10ffd1196091948fb245ff63e406ccb2d4d1) |
+| Source revision | `7edd10ffd1196091948fb245ff63e406ccb2d4d1` |
+| Product family | `qwen3-vl` |
+| Source architecture | `Qwen3VLForConditionalGeneration` (dense); text path optimized |
+| Main-model parameters | 33.36B logical parameters |
+| Quantizer | AXQuant `1.8.1` |
+| Hub budget class | `6bit` |
+| AXQuant base precision class | `8bit` |
+| Planned storage-adjusted BPW | 6.9379 |
+| Measured main-model BPW | 6.9380 |
+| Measured total BPW | **6.9380** |
+| Safetensors weight size | 28.93 GB |
+| Approximate complete download | 28.94 GB |
+| Configured maximum context | 262,144 tokens; practical limits depend on unified memory |
+| Primary MLX runtime | MLX-VLM |
+| AX Engine native execution | Not established; no validated native manifest is included |
+| MTP present | `False` |
+| Vision present | `True` |
+| Audio present | `False` |
+
+This repository contains MLX Safetensors. It does **not** contain PyTorch or GGUF weights.
+
+## Choosing an AXQ pack
+
+AXQ names describe a **storage-budget product class**, not one uniform precision applied to every
+tensor. Protected tensors remain at higher precision, so the exact measured BPW is authoritative.
+In particular, a `6bit`-named mixed plan may retain `4bit` as its base precision while selecting
+6-bit, 8-bit, or BF16 for other tensors to meet an approximately 6-BPW total budget. Protection
+floors can also raise a `4bit`-named pack close to (or above) a `6bit` budget on small or heavily
+protected models. When that collapse happens, AutomatosX does **not** publish a separate
+misleading `4bit` sibling for that base.
+
+
+| Sibling | Intended trade-off |
+| --- | --- |
+| [4bit sibling](https://huggingface.co/AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-4bit) | Lower-storage AXQ budget; check its exact BPW |
+| [6bit sibling](https://huggingface.co/AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit) | Higher average precision near the 6-BPW budget |
+
+See the [AutomatosX collections](https://huggingface.co/AutomatosX/collections)
+for the family catalog, or the [complete index](https://huggingface.co/collections/AutomatosX/automatosx-mlx-model-catalog).
+
+## Download
+
+```bash
+python -m pip install -U huggingface_hub
+hf download AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit --local-dir ./AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit
+```
+
+Allow at least 28.94 GB of free disk space. Pin the resulting Hub commit in reproducible
+deployments rather than relying indefinitely on `main`.
+
+## Run with MLX-VLM
+
+```bash
+python -m pip install -U mlx-vlm
+python -m mlx_vlm.generate \
+  --model AutomatosX/AX-Qwen3-VL-32B-Thinking-MLX-AXQ-6bit \
+  --image ./image.png \
+  --prompt "Describe this image." \
+  --max-tokens 128 \
+  --temperature 0.0
+```
+
+The protected vision tower and AXQ language decoder are loaded together by MLX-VLM. The artifact
+records MLX `0.32.0`; runtime QA is reported separately from model-quality claims.
+
+## AX Engine status
+
+This package does **not** include a validated native `model-manifest.json`, so AX Engine execution
+is not established by this release. The AX Engine fields in `axquant_runtime.json` describe the
+intended compatibility contract, not observed runtime evidence. Use the architecture-specific MLX
+runtime path above. The artifact records AX Engine version
+`not recorded`, but version discovery alone is not a runtime check.
+
+## Quantization layout
+
+| Main-weight precision | Parameters | Share |
+| --- | ---: | ---: |
+| `6bit` | 31.21B | 93.55% |
+| `8bit` | 777.91M | 2.33% |
+| `bf16` | 1.37B | 4.12% |
+
+- Quantization methods: `affine, bf16`.
+- Group sizes used by quantized assignments: `64`.
+- MTP sidecar: not included.
+- Vision sidecar: not included.
+- Vision weights: protected BF16 in main shards.
+- Optimization scope: `text-path`.
+- Support tier: `convertible`.
+
+BF16 sidecars, when present, are included in total download size. Their presence does not by itself
+establish MTP acceleration or vision-language quality.
+
+## Evidence and validation status
+
+| Check | Status |
+| --- | --- |
+| Planning evidence | `architecture_prior` |
+| Calibration | none; the allocation is based on architecture priors |
+| Quantizer execution | 449/449 recorded module conversions succeeded; 0 fallbacks |
+| AX Engine native manifest | not included |
+| Quality versus BF16 or uniform baselines | Not published; no quality-retention claim |
+| MTP acceptance and speed | not measured; no MTP speedup claim |
+| AX Engine kernel evidence | `unmeasured` |
+| Vision-language quality | Present, not certified; text Tier 1 does not imply VLM quality |
+| Speech-recognition quality | Not applicable (audio disabled for this pack) |
+| Long-context quality | 262,144-token capacity is config metadata, not a validated claim |
+| Release certification | **Not certified**; formal AXQuant M0-M8 gates are not closed |
+
+## Modalities (capability-gated)
+
+Text checkpoint Tier 1 does **not** imply vision or audio quality. `Vision present=true` on a pack is not a quality pass.
+
+| Modality | Claim | Supported | Reason |
+| --- | --- | --- | --- |
+| Vision | `present-not-certified` | `true` | vision tower BF16-protected; VL quality not certified |
+| Audio | `not-applicable` | `false` | audio not supported on this pack |
+
+## Intended use and limitations
+
+- Intended for local development and evaluation on Apple Silicon with MLX-compatible runtimes.
+- No minimum unified-memory figure is claimed; loadability depends on model size, context length,
+  KV-cache policy, runtime buffers, and other processes using unified memory.
+- Architecture-prior allocation is not measured sensitivity. It must not be presented as measured
+  model quality.
+- Vision weights are preserved at BF16, but this release does not claim validated VLM quality.
+- The configured context window can require substantially more memory as the KV cache grows.
+- AX Engine execution is not established because this package has no validated native manifest.
+
+- Upstream capabilities, limitations, biases, and responsible-use guidance still apply.
+
+## Provenance and audit files
+
+- [`axquant_manifest.json`](axquant_manifest.json): package identity, byte accounting, runtime
+  contract, software versions, and file checksums.
+- [`axquant_plan.json`](axquant_plan.json): per-tensor precision decisions and planning evidence.
+- [`axquant_quantizer_execution.json`](axquant_quantizer_execution.json): conversion coverage and
+  fallback records.
+- [`axquant_runtime.json`](axquant_runtime.json): declared AX Engine and MLX compatibility metadata; runtime checks remain separate evidence.
+
+All published provenance uses repository-relative paths. Local source paths are stripped before
+publication. The checkpoint was converted from BF16 rather than re-quantized from an OptiQ
+artifact. If an OptiQ repository is published separately, it uses a different quantizer and
+should not be assumed to have identical BPW or quality.
+
+## License
+
+The checkpoint follows the upstream model license where applicable (often Apache License 2.0). See
+the [Qwen/Qwen3-VL-32B-Thinking model card](https://huggingface.co/Qwen/Qwen3-VL-32B-Thinking/tree/7edd10ffd1196091948fb245ff63e406ccb2d4d1) for license terms, model
+limitations, and responsible-use guidance.

axquant_manifest.json

@@ -0,0 +1,492 @@
+{
+  "axquant_version": "1.8.1",
+  "calibration": null,
+  "created_at": "2026-08-15T23:51:25.241690Z",
+  "effective_bpw": 6.937907655843994,
+  "files": [
+    {
+      "path": ".cache/huggingface/.gitignore",
+      "sha256": "684888c0ebb17f374298b65ee2807526c066094c701bcc7ebbe1c1095f494fc1",
+      "size_bytes": 1
+    },
+    {
+      "path": ".cache/huggingface/CACHEDIR.TAG",
+      "sha256": "f6572428f6d5e1575e73a1502895a8731f10757dfbb634909c6e154b849af91d",
+      "size_bytes": 191
+    },
+    {
+      "path": ".cache/huggingface/download/.gitattributes.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/.gitattributes.metadata",
+      "sha256": "5ca3f9fab749b7b27ecfd7f1a8517343da19f42729666a64c3d87ae71090b9df",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/download/README.md.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/README.md.metadata",
+      "sha256": "11c0022f3099c2deebd3095c9d289b5323f4ad5ee7356cf8f83fc87a84c4b82a",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/download/chat_template.json.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/chat_template.json.metadata",
+      "sha256": "646e2437cee7af78f38f8c10a6cb8a182c2f01ac54ea0d92bda3a93315a2fb22",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/download/config.json.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/config.json.metadata",
+      "sha256": "1cbd80d0e12f4dccdf9e5a0f96a09958b8c95b59576ef3caea355bb4fd90e5c2",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/download/generation_config.json.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/generation_config.json.metadata",
+      "sha256": "5bbd52393d500f77f224680b4c6278f0fcfec89537e8e61a93802c135eb7cd34",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/download/merges.txt.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/merges.txt.metadata",
+      "sha256": "240cc6b326f06d613ad7ab40da4081e0043dfed235204db8b79eaa62fcdcda66",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/download/model-00001-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00001-of-00014.safetensors.metadata",
+      "sha256": "026b90c0a36dceeea8ba2b8677ebbb1ac0b8b33009fe3352212a529de66eaeae",
+      "size_bytes": 125
+    },
+    {
+      "path": ".cache/huggingface/download/model-00002-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00002-of-00014.safetensors.metadata",
+      "sha256": "da1755e1bdacaffc9669d478394299444b510fb591cea27f8c2127a48979c923",
+      "size_bytes": 124
+    },
+    {
+      "path": ".cache/huggingface/download/model-00003-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00003-of-00014.safetensors.metadata",
+      "sha256": "cf308016919e1d168f328d1c2b271882561a2ecd1151fc0d216ce4e49ec3a23d",
+      "size_bytes": 124
+    },
+    {
+      "path": ".cache/huggingface/download/model-00004-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00004-of-00014.safetensors.metadata",
+      "sha256": "6078aeb3858168d7973c4621653a5c98bab4b3abc0d7c7ed6e9ca1f27d6b8e99",
+      "size_bytes": 124
+    },
+    {
+      "path": ".cache/huggingface/download/model-00005-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00005-of-00014.safetensors.metadata",
+      "sha256": "f0a22b1de60ef89befcb3fd6da9d6f300a5e288dfd9d1d06dd354599d0534c24",
+      "size_bytes": 124
+    },
+    {
+      "path": ".cache/huggingface/download/model-00006-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00006-of-00014.safetensors.metadata",
+      "sha256": "60e42e7232148697f86205ad8f778cec8042c9b4a6ddd07d2583816bb70404f3",
+      "size_bytes": 124
+    },
+    {
+      "path": ".cache/huggingface/download/model-00007-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00007-of-00014.safetensors.metadata",
+      "sha256": "1507daf4a3c21a23656c4ecf22a8044279e5d9f1f7220b6aafdea8b0b6f5abb2",
+      "size_bytes": 124
+    },
+    {
+      "path": ".cache/huggingface/download/model-00008-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00008-of-00014.safetensors.metadata",
+      "sha256": "49172878b715a70e8d7ecb087f8778283cdc96b2725b5a099541be417c8e4dcc",
+      "size_bytes": 124
+    },
+    {
+      "path": ".cache/huggingface/download/model-00009-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00009-of-00014.safetensors.metadata",
+      "sha256": "b66fead32be7a4d3a5d434349ff94421dba348240154cfc318a1dc45bcfea70c",
+      "size_bytes": 125
+    },
+    {
+      "path": ".cache/huggingface/download/model-00010-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00010-of-00014.safetensors.metadata",
+      "sha256": "14fba5ef9a11c02172d1ca1998cfe73d5bc9c0fad2ac93e44d88488d77e33603",
+      "size_bytes": 125
+    },
+    {
+      "path": ".cache/huggingface/download/model-00011-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00011-of-00014.safetensors.metadata",
+      "sha256": "deb1db61b8a842765f4d3fe11e3b49a866bafdf99632ea611ad8bee4fadca54b",
+      "size_bytes": 124
+    },
+    {
+      "path": ".cache/huggingface/download/model-00012-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00012-of-00014.safetensors.metadata",
+      "sha256": "b3f8cc162b73ccafb50abc46951ec947188d71598d01cdb3e2b95cbb521db795",
+      "size_bytes": 123
+    },
+    {
+      "path": ".cache/huggingface/download/model-00013-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00013-of-00014.safetensors.metadata",
+      "sha256": "b334025d102e0162d28f0abdb308aee6b08f701eaf357216de92355a93da4ba4",
+      "size_bytes": 124
+    },
+    {
+      "path": ".cache/huggingface/download/model-00014-of-00014.safetensors.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model-00014-of-00014.safetensors.metadata",
+      "sha256": "c34d2b7cca72bb0716492fc2e37d55e23840b4da159462743e2104a6a7b3f5f6",
+      "size_bytes": 125
+    },
+    {
+      "path": ".cache/huggingface/download/model.safetensors.index.json.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/model.safetensors.index.json.metadata",
+      "sha256": "b116bbc784716636222b2937dfe7e4f058fcf25af9a5ab78eecbb55336cbebef",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/download/preprocessor_config.json.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/preprocessor_config.json.metadata",
+      "sha256": "32852d0cbb90c6c9def2b333d6b9ca70e3a1e6e862beef4171fe6ba79dae59bc",
+      "size_bytes": 101
+    },
+    {
+      "path": ".cache/huggingface/download/tokenizer.json.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/tokenizer.json.metadata",
+      "sha256": "7778be585e981980c7bcae69abc920f16629a97e1e27c9302a86f0739d7fbe47",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/download/tokenizer_config.json.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/tokenizer_config.json.metadata",
+      "sha256": "858e5dffbec632c6299e3c72a003d78a9b578c57fd7288a69c7a3d397ec2572f",
+      "size_bytes": 99
+    },
+    {
+      "path": ".cache/huggingface/download/video_preprocessor_config.json.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/video_preprocessor_config.json.metadata",
+      "sha256": "4de7528e59f299bd683ed08b4b54377b48a20564a01cc566081e280b9165e098",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/download/vocab.json.lock",
+      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "size_bytes": 0
+    },
+    {
+      "path": ".cache/huggingface/download/vocab.json.metadata",
+      "sha256": "89532a396d926d4fc17e200bdc5916010f58ddd5b4adc529f0c65333f11eed68",
+      "size_bytes": 100
+    },
+    {
+      "path": ".cache/huggingface/trees/7edd10ffd1196091948fb245ff63e406ccb2d4d1.json",
+      "sha256": "6ec1388f4dbe5f5e4ea9a9f90b8f753fc0af4c99fbd6f940926b0a8466de9f66",
+      "size_bytes": 5782
+    },
+    {
+      "path": "README.md",
+      "sha256": "71c38e6eeff76f0eae1d295138e5496d6994be5f1c1d297de966c66c8863fdd8",
+      "size_bytes": 8247
+    },
+    {
+      "path": "axquant_plan.json",
+      "sha256": "25a4a4f1c45a680e226e1e1338756657d19eeb574747b36361bbe956ca41dd3c",
+      "size_bytes": 964238
+    },
+    {
+      "path": "axquant_quantizer_execution.json",
+      "sha256": "b77f6d2df081884bca5b7a79aae1033fdcdf867cd49a963b9bf5fee54f16c0c8",
+      "size_bytes": 116609
+    },
+    {
+      "path": "axquant_runtime.json",
+      "sha256": "aa7752af89fec85495a7c2f3ac2b5850d6e56e904e38a67cf5ecfc5f9b0c8641",
+      "size_bytes": 1224
+    },
+    {
+      "path": "chat_template.jinja",
+      "sha256": "36e042fe45641f067b1f2381fcc8955d10d956a3ed333ecdf7f7eb0916f68956",
+      "size_bytes": 5199
+    },
+    {
+      "path": "chat_template.json",
+      "sha256": "efad756db13feb8e8c5fe1341713bf18b82e91916b978d36b7c043f2b1bedf5f",
+      "size_bytes": 5410
+    },
+    {
+      "path": "config.json",
+      "sha256": "08cb9fdc289e8d3b5fb5b0468a183657d501e6426fc95991678b966d6ac6f630",
+      "size_bytes": 139126
+    },
+    {
+      "path": "generation_config.json",
+      "sha256": "1f0843f01e1f468a71ddec33c3c532957ee918fc551932e4508d253a02273f99",
+      "size_bytes": 270
+    },
+    {
+      "path": "model-00001-of-00006.safetensors",
+      "sha256": "4620ece4c9475aa89fac602e6a1ee030e3bd1beabeba341632eb5a208fd67a6b",
+      "size_bytes": 5365720846
+    },
+    {
+      "path": "model-00002-of-00006.safetensors",
+      "sha256": "9694854af2c7e1bff9e297c0e1b6b39b7b9fb5cbc07c6c5bcd824a9799390177",
+      "size_bytes": 5367550438
+    },
+    {
+      "path": "model-00003-of-00006.safetensors",
+      "sha256": "422221160109777ea3098c6ef0099fba37d2884f64cfb39fa829047f0a966579",
+      "size_bytes": 5333658096
+    },
+    {
+      "path": "model-00004-of-00006.safetensors",
+      "sha256": "88e6e7eae7b4eb3d1735baf478504eb81d27761770a4ed074f64d3a17313b8e7",
+      "size_bytes": 5363454335
+    },
+    {
+      "path": "model-00005-of-00006.safetensors",
+      "sha256": "d3850fdf94da741c091f628b1587bbd52ed535f0d0bb6c28dcfbffd5da870b6b",
+      "size_bytes": 5333658172
+    },
+    {
+      "path": "model-00006-of-00006.safetensors",
+      "sha256": "ec710f6888c1893ecf6647a0ee4c9a5d17a6a5be05906c6950cdb9896223d68a",
+      "size_bytes": 2165017255
+    },
+    {
+      "path": "model.safetensors.index.json",
+      "sha256": "b33c78770d2c1dafb8ed8432a4020855ad8aafcd269b474500d7ada587883634",
+      "size_bytes": 192109
+    },
+    {
+      "path": "preprocessor_config.json",
+      "sha256": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516",
+      "size_bytes": 390
+    },
+    {
+      "path": "processor_config.json",
+      "sha256": "45fc17c8dd2474af6b493b52483c26c0584b0082d368c480f9fa611e73070040",
+      "size_bytes": 991
+    },
+    {
+      "path": "tokenizer.json",
+      "sha256": "be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506",
+      "size_bytes": 11422650
+    },
+    {
+      "path": "tokenizer_config.json",
+      "sha256": "7ce86d685d3fb775073b9b1c0f576dd89b7943194c771dd2573cc10e5cae4a48",
+      "size_bytes": 734
+    },
+    {
+      "path": "video_preprocessor_config.json",
+      "sha256": "7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13",
+      "size_bytes": 385
+    },
+    {
+      "path": "vocab.json",
+      "sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
+      "size_bytes": 2776833
+    }
+  ],
+  "format": "mlx",
+  "logical_parameters": 33357390064,
+  "main_logical_parameters": 33357390064,
+  "main_weight_file_size_bytes": 28929059142,
+  "measured_main_bpw": 6.937967049939163,
+  "measured_total_bpw": 6.937967049939163,
+  "mtp_acceptance_retention": null,
+  "mtp_distribution": {},
+  "mtp_measured_speedup": null,
+  "mtp_policy": {
+    "candidate_bits": [
+      8,
+      16
+    ],
+    "min_bits": 8,
+    "mode": "protected",
+    "optimize_for_acceptance": true,
+    "preserve_external_sidecar": true,
+    "protect_norms": true,
+    "protect_output_head": true
+  },
+  "mtp_present": false,
+  "mtp_weight_file_size_bytes": 0,
+  "plan_sha256": "e1d645a769710bfaced7dc08dcc7f35ab6f37dae91eb941a6e510b97ed256a5e",
+  "profile": "agent-coding",
+  "protected_weight_file_size_bytes": 0,
+  "quantizer": "axquant",
+  "runtime": {
+    "ax_engine": {
+      "decode_kernel": null,
+      "fused_mtp": null,
+      "kernel_evidence": "unmeasured",
+      "model_manifest": "model-manifest.json",
+      "preferred_group_size": 64
+    },
+    "compatible_runtimes": [],
+    "created_at": "2026-08-15T23:51:11.870594Z",
+    "kv_cache": null,
+    "memory_policy": {
+      "kv_cache_precision": "runtime-default",
+      "mtp_buffers": "not-required",
+      "prefix_cache": "runtime-managed",
+      "unified_memory_safety_margin": "benchmark-required"
+    },
+    "mtp": {
+      "acceptance_retention": null,
+      "detected": false,
+      "draft_tokens": null,
+      "enabled_by_default": false,
+      "head_precision": null,
+      "measured_speedup": null,
+      "optimized": false,
+      "recommended_temperature_max": null,
+      "sidecar_file": null,
+      "verification_mode": null
+    },
+    "optimization_scope": "text-path",
+    "primary_runtime": {
+      "compatibility_level": "A",
+      "manifest": "config.json",
+      "mtp_support": "none",
+      "name": "mlx-vlm",
+      "notes": [
+        "MLX-VLM loads the protected modality tower and AXQ language decoder."
+      ],
+      "standard_inference": true,
+      "standard_mlx_weights": true,
+      "support_level": "standard-inference"
+    },
+    "schema_version": "axquant.runtime.v1"
+  },
+  "schema_version": "axquant.artifact.v2",
+  "software_versions": {
+    "ax_engine": null,
+    "axquant": "1.8.1",
+    "mlx": "0.32.0",
+    "mlx_lm": "0.31.3",
+    "pydantic": "2.13.4",
+    "python": "3.12.13",
+    "safetensors": "0.8.0"
+  },
+  "source_model": {
+    "architecture": "Qwen3VLForConditionalGeneration",
+    "format": "mlx",
+    "local_path": null,
+    "model_id": "Qwen/Qwen3-VL-32B-Thinking",
+    "revision": "7edd10ffd1196091948fb245ff63e406ccb2d4d1"
+  },
+  "target_class": "8bit",
+  "weight_distribution": {
+    "6bit": {
+      "fraction": 0.9354935053410478,
+      "parameters": 31205621760
+    },
+    "8bit": {
+      "fraction": 0.023320539122140115,
+      "parameters": 777912320
+    },
+    "bf16": {
+      "fraction": 0.04118595553681205,
+      "parameters": 1373855984
+    }
+  },
+  "weight_file_size_bytes": 28929059142
+}

axquant_runtime.json

@@ -0,0 +1,44 @@
+{
+  "ax_engine": {
+    "decode_kernel": null,
+    "fused_mtp": null,
+    "kernel_evidence": "unmeasured",
+    "model_manifest": "model-manifest.json",
+    "preferred_group_size": 64
+  },
+  "compatible_runtimes": [],
+  "created_at": "2026-08-15T23:51:11.870594Z",
+  "kv_cache": null,
+  "memory_policy": {
+    "kv_cache_precision": "runtime-default",
+    "mtp_buffers": "not-required",
+    "prefix_cache": "runtime-managed",
+    "unified_memory_safety_margin": "benchmark-required"
+  },
+  "mtp": {
+    "acceptance_retention": null,
+    "detected": false,
+    "draft_tokens": null,
+    "enabled_by_default": false,
+    "head_precision": null,
+    "measured_speedup": null,
+    "optimized": false,
+    "recommended_temperature_max": null,
+    "sidecar_file": null,
+    "verification_mode": null
+  },
+  "optimization_scope": "text-path",
+  "primary_runtime": {
+    "compatibility_level": "A",
+    "manifest": "config.json",
+    "mtp_support": "none",
+    "name": "mlx-vlm",
+    "notes": [
+      "MLX-VLM loads the protected modality tower and AXQ language decoder."
+    ],
+    "standard_inference": true,
+    "standard_mlx_weights": true,
+    "support_level": "standard-inference"
+  },
+  "schema_version": "axquant.runtime.v1"
+}

chat_template.jinja

@@ -0,0 +1,110 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- else %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                <|vision_start|><|image_pad|><|vision_end|>
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                <|vision_start|><|video_pad|><|vision_end|>
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{%- endmacro %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- render_content(messages[0].content, false) + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false) %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, True) %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n<think>\n' }}
+{%- endif %}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- else %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                <|vision_start|><|image_pad|><|vision_end|>\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                <|vision_start|><|video_pad|><|vision_end|>\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- endif %}\n        {%- endfor %}\n    {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- render_content(messages[0].content, false) + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false) %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, True) %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n"
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+    "bos_token_id": 151643,
+    "pad_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "top_k": 20,
+    "top_p": 0.95,
+    "repetition_penalty": 1.0,
+    "temperature": 0.8,
+    "transformers_version": "4.56.0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4620ece4c9475aa89fac602e6a1ee030e3bd1beabeba341632eb5a208fd67a6b
+size 5365720846

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9694854af2c7e1bff9e297c0e1b6b39b7b9fb5cbc07c6c5bcd824a9799390177
+size 5367550438

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422221160109777ea3098c6ef0099fba37d2884f64cfb39fa829047f0a966579
+size 5333658096

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e6e7eae7b4eb3d1735baf478504eb81d27761770a4ed074f64d3a17313b8e7
+size 5363454335

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3850fdf94da741c091f628b1587bbd52ed535f0d0bb6c28dcfbffd5da870b6b
+size 5333658172

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec710f6888c1893ecf6647a0ee4c9a5d17a6a5be05906c6950cdb9896223d68a
+size 2165017255

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor_config.json

@@ -0,0 +1,50 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen3VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_pixels": 16777216,
+    "merge_size": 2,
+    "min_pixels": 65536,
+    "patch_size": 16,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "fps": 2.0,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "max_pixels": 25165824,
+    "merge_size": 2,
+    "min_frames": 4,
+    "min_pixels": 4096,
+    "patch_size": 16,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}