Duplicate from empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

Co-authored-by: Empero <empero-ai@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,47 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+Qwythos-9B-Claude-Mythos-5-1M-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwythos-9B-Claude-Mythos-5-1M-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwythos-9B-Claude-Mythos-5-1M-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwythos-9B-Claude-Mythos-5-1M-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-Qwythos-9B-Claude-Mythos-5-1M-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwythos-9B-Claude-Mythos-5-1M-MTP-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwythos-9B-Claude-Mythos-5-1M-MTP-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwythos-9B-Claude-Mythos-5-1M-MTP-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwythos-9B-Claude-Mythos-5-1M-MTP-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Qwythos-9B-Claude-Mythos-5-1M-BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49e2e419c0fc9f7cca0a7e0699fa3075fa1ec2913bda6f6841194b19cf4ce29
+size 17920697344

Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c704996e63c3e31a1e7040278b1204aabf8a6dad0b07f3c8da7b429d2ed30b31
+size 18407321536

Qwythos-9B-Claude-Mythos-5-1M-MTP-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ee22e0f5d9f0d3d615809607f365c728d9b0c3f3fb6eb19d8bd83a1c2933d8
+size 5887668160

Qwythos-9B-Claude-Mythos-5-1M-MTP-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e3c47b17a93cc1566abcee4a0c9a4413b172a6f8be7f2a8824495907e9e893
+size 6726528960

Qwythos-9B-Claude-Mythos-5-1M-MTP-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae2adb4b451f673218fba96ebdc024fb95c4026ef35a56837dc9af47f99ca39
+size 7617818560

Qwythos-9B-Claude-Mythos-5-1M-MTP-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34eada291b4f4d1b8592f53d1739c7a2e029011b5bc2624b979b0a544562a5e9
+size 9786060736

Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de41ff56ab4eff26764437b276f0bd5d20f44232add34e14c4f593fa1aeb08f
+size 5629109248

Qwythos-9B-Claude-Mythos-5-1M-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51dee6e6ddaeb08a06bee258ac5c58f4186f55d156d6403c2db67cf2f3226280
+size 6467970048

Qwythos-9B-Claude-Mythos-5-1M-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f2420a669a83ae239d1328c6e83d9fc19e8a4b8dab5d0673cab28cc161dfc5
+size 7359259648

Qwythos-9B-Claude-Mythos-5-1M-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf51ef3904694e04a1967a06fe7539619c34e6e81a721fc5f5415827081d8f6
+size 9527501824

README.md

@@ -0,0 +1,247 @@
+---
+license: apache-2.0
+base_model: empero-ai/Qwythos-9B-Claude-Mythos-5-1M
+base_model_relation: quantized
+language:
+  - en
+pipeline_tag: text-generation
+library_name: gguf
+tags:
+  - gguf
+  - llama.cpp
+  - quantized
+  - qwen3.5
+  - reasoning
+  - uncensored
+  - long-context
+  - 1M-context
+  - function-calling
+  - multimodal
+  - vision
+  - cybersecurity
+  - biomedical
+  - agentic
+---
+
+<p align="center">
+  <img src="https://huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M/resolve/main/assets/qwythos.png" alt="Qwythos-9B" width="640"/>
+</p>
+
+<table>
+<tr>
+<td>
+
+## 🚨 v2 released — please redownload the GGUFs
+
+The v2 GGUFs replace the original normal filenames and add explicit `-MTP-` variants. If you downloaded this repo before v2, please redownload your GGUF.
+
+Fixes in v2:
+
+- tokenizer metadata normalized for Qwen3.5 GGUF runtimes;
+- embedded chat template updated for reliable tool/function calling and OpenCode-style agent loops;
+- Qwythos/Empero identity prompt embedded in the template;
+- MTP-enabled variants added as `Qwythos-9B-Claude-Mythos-5-1M-MTP-*.gguf`;
+- Q4/Q8 tool-calling, MTP draft speculation, 1M-context allocation, and vision projector smoke-tested with current llama.cpp.
+
+Use the normal files for maximum runtime compatibility. Use the `-MTP-` files when you want llama.cpp MTP draft speculation.
+
+</td>
+</tr>
+</table>
+
+# Qwythos-9B-Claude-Mythos-5-1M-GGUF
+
+**Developed by [Empero](https://empero.org)**
+
+GGUF quantizations of **[empero-ai/Qwythos-9B-Claude-Mythos-5-1M](https://huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M)** for [llama.cpp](https://github.com/ggml-org/llama.cpp), Ollama, LM Studio, jan, KoboldCpp, and other GGUF runtimes.
+
+Qwythos-9B is a full-parameter reasoning model post-trained on over 500 million tokens of high-quality Claude Mythos / Claude Fable traces with chain-of-thought generated in-house by Empero AI's internal `rethink` tool. It dominates the base Qwen3.5-9B under matched evaluation (**+34 pts MMLU, +30 pts gsm8k-strict, +19 pts gsm8k-flex**), supports **native function calling** per the Qwen3.5 spec, and ships with a **1,048,576-token (1M) context window** via YaRN rope-scaling enabled by default.
+
+For full training details, evaluation numbers, and capability writeup, see the **[base model card](https://huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M)**.
+
+---
+
+## Files
+
+### Normal text weights — fixed v2 replacements
+
+| File | Quant | Size | Notes |
+|---|---|---|---|
+| `Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf` | Q4_K_M | 5.24 GiB / 5.63 GB | **recommended default** — fixed v2, best compatibility |
+| `Qwythos-9B-Claude-Mythos-5-1M-Q5_K_M.gguf` | Q5_K_M | 6.02 GiB / 6.47 GB | fixed v2, balanced quality / size |
+| `Qwythos-9B-Claude-Mythos-5-1M-Q6_K.gguf` | Q6_K | 6.85 GiB / 7.36 GB | fixed v2, high quality |
+| `Qwythos-9B-Claude-Mythos-5-1M-Q8_0.gguf` | Q8_0 | 8.87 GiB / 9.53 GB | fixed v2, near-lossless |
+| `Qwythos-9B-Claude-Mythos-5-1M-BF16.gguf` | BF16 | 16.69 GiB / 17.92 GB | fixed v2, full precision conversion base |
+
+If you don't know which to pick, **Q4_K_M is the right starting point** — it's the smallest practical quant with good quality preservation.
+
+### MTP-enabled text weights — v2 variants
+
+These include the restored Qwen3.5-compatible MTP head inside the GGUF. Use them with llama.cpp builds that support MTP draft speculation, for example `--spec-type draft-mtp`.
+
+| File | Quant | Size | Notes |
+|---|---|---|---|
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-Q4_K_M.gguf` | Q4_K_M + MTP | 5.48 GiB / 5.89 GB | **recommended MTP default** |
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-Q5_K_M.gguf` | Q5_K_M + MTP | 6.26 GiB / 6.73 GB | MTP, balanced quality / size |
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-Q6_K.gguf` | Q6_K + MTP | 7.09 GiB / 7.62 GB | MTP, high quality |
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-Q8_0.gguf` | Q8_0 + MTP | 9.11 GiB / 9.79 GB | MTP, near-lossless |
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16.gguf` | BF16 + MTP | 17.14 GiB / 18.41 GB | MTP, full precision conversion base |
+
+### Vision projector — for image input
+
+| File | Size | Notes |
+|---|---|---|
+| `mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf` | 0.86 GiB / 0.92 GB | CLIP-style vision encoder + projector; **required for images**, pairs with any normal or MTP quant above |
+
+Qwythos inherits its **vision tower from the Qwen3.5-9B base model** — the vision path was *frozen* during SFT (training was text-only), so the vision behavior is identical to base Qwen3.5-9B's multimodal capability. The mmproj is interchangeable with any community-built Qwen3.5-9B `mmproj-*.gguf`.
+
+---
+
+## Quick start
+
+### llama.cpp (`llama-cli`)
+
+```bash
+llama-cli \
+  -m Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf \
+  -p "Walk through the biochemistry of how organophosphate nerve agents inhibit acetylcholinesterase." \
+  -n 8192 \
+  --temp 0.6 --top-p 0.95 --top-k 20 --repeat-penalty 1.05 \
+  -c 16384
+```
+
+### Ollama
+
+```bash
+ollama run hf.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
+```
+
+### LM Studio / jan / KoboldCpp
+
+Drop any of the `.gguf` files into your runtime's model directory. Qwythos uses the standard Qwen3.5 chat template; modern GGUF runtimes load it automatically from the file.
+
+### llama.cpp with MTP draft speculation
+
+```bash
+llama-server \
+  -m Qwythos-9B-Claude-Mythos-5-1M-MTP-Q4_K_M.gguf \
+  --spec-type draft-mtp \
+  --spec-draft-n-max 6 \
+  -c 16384 --port 8080
+```
+
+MTP support requires a recent llama.cpp build. If your runtime does not support MTP yet, use the normal v2 files above.
+
+---
+
+## Vision (image input)
+
+Qwythos supports **image input** out of the box. Download both a text quant and the `mmproj-*.gguf` file from this repo, then run with llama.cpp's multimodal CLI or server.
+
+### llama.cpp (`llama-mtmd-cli`)
+
+```bash
+llama-mtmd-cli \
+  -m Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf \
+  --mmproj mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf \
+  --image ./photo.jpg \
+  -p "Describe this image in detail." \
+  --temp 0.6 --top-p 0.95 --top-k 20 \
+  -c 16384
+```
+
+### llama.cpp server (OpenAI-compatible API with images)
+
+```bash
+llama-server \
+  -m Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf \
+  --mmproj mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf \
+  -c 16384 --port 8080
+```
+
+Then POST to `/v1/chat/completions` with an image URL or base64 payload — the standard OpenAI vision API shape works.
+
+### LM Studio
+
+Load the text quant; LM Studio detects the matching `mmproj-*.gguf` in the same folder and enables the image-attach button automatically.
+
+### What vision unlocks
+
+Since Qwythos inherits its vision tower unchanged from Qwen3.5-9B base, expect Qwen3.5-9B's documented vision capabilities: detailed image description, OCR (printed + handwritten), chart/table reading, UI/document understanding, basic spatial reasoning.
+
+**Honest note:** the SFT used to produce Qwythos was **text-only** — we did not fine-tune the vision tower or train on any image-paired data. Image-grounded reasoning therefore inherits the base model's behavior; it has not been independently evaluated as part of this release. If your application is *primarily* vision-driven, validate on your own use case first.
+
+---
+
+## Sampling recommendations
+
+Qwythos is a reasoning model — every response opens with a `<think>...</think>` block before the final answer. Use these settings as defaults:
+
+| Parameter | Value |
+|---|---|
+| `temperature` | 0.6 |
+| `top_p` | 0.95 |
+| `top_k` | 20 |
+| `repeat_penalty` | 1.05 |
+| `max_new_tokens` | 16384 (generous budget for `<think>` + answer) |
+
+These match Qwen3.5's official thinking-mode recommendations. **Avoid greedy decoding and very-low-temperature sampling (T ≤ 0.3)** — both can cause repetition loops on long reasoning generations.
+
+---
+
+## Long context (1M tokens)
+
+The GGUFs ship with YaRN rope-scaling baked in for a **1,048,576-token context window** (4× extension over the 262k native).
+
+To use the full 1M window in `llama-cli`, set `-c 1010000` (or any context length up to that). For shorter prompts, lower `-c` to reduce KV-cache memory — at default settings llama.cpp will autosize.
+
+A single H100/H200-class GPU comfortably handles **256k–512k**; the full 1M typically needs tensor-parallel multi-GPU or aggressive KV-cache offload.
+
+---
+
+## Capabilities (from the base model card)
+
+- **+34 pts MMLU, +30 pts gsm8k-strict, +19 pts gsm8k-flex** vs. base Qwen3.5-9B under matched lm-eval-harness evaluation
+- **Native function calling** per Qwen3.5's chat-template spec — emits `<tool_call><function=NAME><parameter=NAME>VAL</parameter></function></tool_call>` blocks ready for any tool-use loop
+- **Self-correcting with tools**: in a 7-prompt tool-use harness (Python executor + DuckDuckGo search), Qwythos produced source-cited correct answers on 7/7, including 4/4 closed-book failure-modes from the original review
+- **Uncensored** — engages seriously with technically demanding questions across cybersecurity, red-teaming, biology, pharmacology, and clinical medicine
+- **1,048,576-token (1M) context** — YaRN rope-scaling enabled by default
+
+For full eval transcripts and per-task numbers, see the [base model card's `evals/` folder](https://huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M/tree/main/evals).
+
+---
+
+## Limitations
+
+- **Reasoning model.** Every answer opens with a `<think>` block; allow generous `max_new_tokens` and parse/strip `<think>...</think>` for end users.
+- **Use recommended sampling.** Greedy / very-low-temp can cause repetition loops.
+- **Verify specifics in safety-critical contexts.** Like all closed-book LLMs in this weight class, Qwythos can over-commit to specific identifiers (CVEs, hashcat modes, drug positions) it isn't certain about. Pair with retrieval or function calling in such deployments — the model uses tools cleanly when offered them.
+- **Uncensored — add your own application-level review/safety layer** for end-user-facing deployments where that matters.
+
+---
+
+## Stay in the loop
+
+Sign up for the Empero newsletter at **[empero.org](https://empero.org)** for releases, evals, and research notes.
+
+## Support / Donate
+
+If this model helped you, consider supporting the project:
+
+- **BTC**: `bc1qx6zepu6sfkvshgdmc4ewu6pk6rpadvpgffpp7v`
+- **LTC**: `ltc1qv2mefzps2vtjcpwfx8xxdrpplrcvltswm68r7x`
+- **XMR**: `42Dbm5xg5Nq26fdyzfEU7KBnAJfhi7Cvz5J2ex5CzHXkfKuNEJzYCcmJ1GTbgjFZ5MBx72sdG1G9239Cd6rsZfv4QeDkYJY`
+
+---
+
+## Provenance & licensing
+
+Weights are released under **Apache-2.0**, inherited from the Qwen3.5-9B base. Shared for research and experimentation, as-is.
+
+## Acknowledgements
+
+- Developed and released by [Empero](https://empero.org)
+- Base model: [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) (Alibaba Qwen team)
+- Quantization: [llama.cpp](https://github.com/ggml-org/llama.cpp) (ggml-org)
+- Vision projector (`mmproj`): inherited from Qwen3.5-9B (vision tower unchanged); F16 GGUF re-hosted with thanks to [Unsloth](https://huggingface.co/unsloth) for the original conversion
+- HF model: [empero-ai/Qwythos-9B-Claude-Mythos-5-1M](https://huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M)

SHA256SUMS

@@ -0,0 +1,11 @@
+c49e2e419c0fc9f7cca0a7e0699fa3075fa1ec2913bda6f6841194b19cf4ce29  ./Qwythos-9B-Claude-Mythos-5-1M-BF16.gguf
+c704996e63c3e31a1e7040278b1204aabf8a6dad0b07f3c8da7b429d2ed30b31  ./Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16.gguf
+24ee22e0f5d9f0d3d615809607f365c728d9b0c3f3fb6eb19d8bd83a1c2933d8  ./Qwythos-9B-Claude-Mythos-5-1M-MTP-Q4_K_M.gguf
+c4e3c47b17a93cc1566abcee4a0c9a4413b172a6f8be7f2a8824495907e9e893  ./Qwythos-9B-Claude-Mythos-5-1M-MTP-Q5_K_M.gguf
+eae2adb4b451f673218fba96ebdc024fb95c4026ef35a56837dc9af47f99ca39  ./Qwythos-9B-Claude-Mythos-5-1M-MTP-Q6_K.gguf
+34eada291b4f4d1b8592f53d1739c7a2e029011b5bc2624b979b0a544562a5e9  ./Qwythos-9B-Claude-Mythos-5-1M-MTP-Q8_0.gguf
+0de41ff56ab4eff26764437b276f0bd5d20f44232add34e14c4f593fa1aeb08f  ./Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf
+51dee6e6ddaeb08a06bee258ac5c58f4186f55d156d6403c2db67cf2f3226280  ./Qwythos-9B-Claude-Mythos-5-1M-Q5_K_M.gguf
+05f2420a669a83ae239d1328c6e83d9fc19e8a4b8dab5d0673cab28cc161dfc5  ./Qwythos-9B-Claude-Mythos-5-1M-Q6_K.gguf
+ecf51ef3904694e04a1967a06fe7539619c34e6e81a721fc5f5415827081d8f6  ./Qwythos-9B-Claude-Mythos-5-1M-Q8_0.gguf
+f977efc337a2ac2ba183eea0c73e25b75fc240d56c05ed4d9b56ab451f64c82c  ./mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf

TEST_REPORT.md

@@ -0,0 +1,53 @@
+# Qwythos GGUF v2 release verification
+
+Release verification was performed on 2026-06-22 with llama.cpp `d0f9d2e5ac5d4f51763755958b8f353fed01aaa2` and an NVIDIA RTX 5090.
+
+## Artifact manifest
+
+| Artifact | Bytes | SHA-256 |
+|---|---:|---|
+| `Qwythos-9B-Claude-Mythos-5-1M-BF16.gguf` | 17,920,697,344 | `c49e2e419c0fc9f7cca0a7e0699fa3075fa1ec2913bda6f6841194b19cf4ce29` |
+| `Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf` | 5,629,109,248 | `0de41ff56ab4eff26764437b276f0bd5d20f44232add34e14c4f593fa1aeb08f` |
+| `Qwythos-9B-Claude-Mythos-5-1M-Q5_K_M.gguf` | 6,467,970,048 | `51dee6e6ddaeb08a06bee258ac5c58f4186f55d156d6403c2db67cf2f3226280` |
+| `Qwythos-9B-Claude-Mythos-5-1M-Q6_K.gguf` | 7,359,259,648 | `05f2420a669a83ae239d1328c6e83d9fc19e8a4b8dab5d0673cab28cc161dfc5` |
+| `Qwythos-9B-Claude-Mythos-5-1M-Q8_0.gguf` | 9,527,501,824 | `ecf51ef3904694e04a1967a06fe7539619c34e6e81a721fc5f5415827081d8f6` |
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16.gguf` | 18,407,321,536 | `c704996e63c3e31a1e7040278b1204aabf8a6dad0b07f3c8da7b429d2ed30b31` |
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-Q4_K_M.gguf` | 5,887,668,160 | `24ee22e0f5d9f0d3d615809607f365c728d9b0c3f3fb6eb19d8bd83a1c2933d8` |
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-Q5_K_M.gguf` | 6,726,528,960 | `c4e3c47b17a93cc1566abcee4a0c9a4413b172a6f8be7f2a8824495907e9e893` |
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-Q6_K.gguf` | 7,617,818,560 | `eae2adb4b451f673218fba96ebdc024fb95c4026ef35a56837dc9af47f99ca39` |
+| `Qwythos-9B-Claude-Mythos-5-1M-MTP-Q8_0.gguf` | 9,786,060,736 | `34eada291b4f4d1b8592f53d1739c7a2e029011b5bc2624b979b0a544562a5e9` |
+| `mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf` | 918,165,472 | `f977efc337a2ac2ba183eea0c73e25b75fc240d56c05ed4d9b56ab451f64c82c` |
+
+`shasum -a 256 -c SHA256SUMS` passed for all 11 GGUF artifacts after conversion and testing.
+
+## Structural checks
+
+All ten text GGUFs passed these shared assertions:
+
+- GGUF v3 and `qwen35` architecture;
+- 1,048,576-token declared context;
+- Qwen3.6-derived chat template markers present;
+- fixed Qwythos/Empero AI identity instruction present.
+
+The five normal v2 replacement files additionally verified as 32-block trunk-only GGUFs with no `nextn_predict_layers` key and no MTP tensors.
+
+The five `-MTP-` v2 variants additionally verified as 33-block GGUFs with `qwen35.nextn_predict_layers = 1`, all 15 restored MTP tensors present, and MTP matrices retained at Q8_0 in every quantized variant.
+
+The MTP tensors come from pinned Qwen3.5-9B base commit `c202236235762e1c871ad0ccb60c8ee5ba337b9a`. The source fine-tune declares one MTP layer but does not publish its MTP tensors. Only the draft head is restored; the Qwythos trunk and output layers remain unchanged.
+
+## Live tests
+
+| Variant / mode | Identity | Generation | Tools | Other |
+|---|---:|---:|---:|---|
+| BF16 MTP | Pass | Pass | — | — |
+| Q4_K_M MTP | Pass | Pass | Pass | Tool result round trip passed |
+| Q5_K_M MTP | Pass | Pass | — | — |
+| Q6_K MTP | Pass | Pass | — | — |
+| Q8_0 MTP | Pass | Pass | Pass | Tool result round trip passed; no malformed output |
+| Q4_K_M MTP + draft speculation | Pass | Pass | Pass | 76/150 draft tokens accepted (50.7%) |
+| Q4_K_M MTP + 1M context | Pass | Pass | — | Server loaded `n_ctx = 1048576` |
+| Q4_K_M MTP + F16 mmproj | Pass | Pass | — | Correctly identified a generated red-square image |
+
+The normal v2 replacement files were rebuilt from the same fixed tokenizer/template source with `--no-mtp` and structurally verified after quantization. The 1M-context check verifies full context allocation and successful generation at that setting; it is not a million-token retrieval benchmark.
+
+Machine-readable responses are in `reports/`; relevant llama.cpp logs are in `logs/`.

mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f977efc337a2ac2ba183eea0c73e25b75fc240d56c05ed4d9b56ab451f64c82c
+size 918165472

mmproj-Qwythos-9B-Claude-Mythos-5-1M-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70dc3509053962b0d0d3ee8a7eacebf5d60aa560cad78254ae8698516ae029f
+size 918166080