Upload a Text-Only GGUF models

.gitattributes

@@ -33,3 +33,11 @@ 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
+Qwen3.5-text-0.8B-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-text-0.8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-text-0.8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-text-0.8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-text-0.8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.5-text-0.8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+diagrams/diagram_01.png filter=lfs diff=lfs merge=lfs -text
+diagrams/diagram_02.png filter=lfs diff=lfs merge=lfs -text

Qwen3.5-text-0.8B-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb54ae1ebaa62fb9ed17d7cd28a90920a6530ae3645a2636c9c01f8023a23b0a
+size 1516743392

Qwen3.5-text-0.8B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff92d3f680206e355119b14682846972c40ec95ebdf9c9a28881be1615fa794
+size 527502048

Qwen3.5-text-0.8B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaad169d2b555d8c7c92cb9eb9c40751572765b1a2521f7314e9205f8df65fa3
+size 503089888

Qwen3.5-text-0.8B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631bfef7d6a8e5fd81f22dc38b816bc7d23aa0a615430baee4463b7ea7360115
+size 584821472

Qwen3.5-text-0.8B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1f545d66c2c0f75825b2d2f5bb9f49f30e35aa323efefde23f16b3b0a8dcbc
+size 629742816

Qwen3.5-text-0.8B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df90690d9d482ccd76b768a8249dc3d05a1f712992b7f598be88a2895d9f3b7
+size 811842272

README.md

@@ -0,0 +1,95 @@
+---
+tags:
+- techwithsergiu
+- gguf
+library_name: gguf
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3.5-0.8B/blob/main/LICENSE
+pipeline_tag: text-generation
+base_model:
+- techwithsergiu/Qwen3.5-text-0.8B
+---
+
+# Qwen3.5-text-0.8B-GGUF
+
+<img width="400px" src="https://qianwen-res.oss-accelerate.aliyuncs.com/logo_qwen3.5.png">
+
+GGUF quants of [techwithsergiu/Qwen3.5-text-0.8B](https://huggingface.co/techwithsergiu/Qwen3.5-text-0.8B) —
+the text-only bf16 derivative of [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B).
+
+The visual tower has been removed before conversion. All text-backbone weights are
+**identical** to the original — no retraining, no weight changes, no quality loss for
+text tasks.
+
+## Quants
+
+| File | Type | Size | Notes |
+|---|---|---|---|
+| `Qwen3.5-text-0.8B-Q8_0.gguf` | Q8_0 | ~53% of f16 | near-lossless — for high-quality inference |
+| `Qwen3.5-text-0.8B-Q6_K.gguf` | Q6_K | ~41% of f16 | excellent quality, good balance with f16 |
+| `Qwen3.5-text-0.8B-Q5_K_M.gguf` | Q5_K_M | ~37% of f16 | very good quality, smaller than Q6 |
+| `Qwen3.5-text-0.8B-Q4_K_M.gguf` | Q4_K_M | ~31% of f16 | ✅ recommended — best size/quality balance |
+| `Qwen3.5-text-0.8B-Q4_K_S.gguf` | Q4_K_S | ~30% of f16 | optional — slightly smaller, slightly lower quality |
+
+## Model family
+
+![](diagrams/diagram_01.png)
+
+| Model | Type | Base model |
+|---|---|---|
+| [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) | f16 · VLM · source | — |
+| [techwithsergiu/Qwen3.5-0.8B-bnb-4bit](https://huggingface.co/techwithsergiu/Qwen3.5-0.8B-bnb-4bit) | BNB NF4 · VLM | Qwen/Qwen3.5-0.8B |
+| [techwithsergiu/Qwen3.5-text-0.8B](https://huggingface.co/techwithsergiu/Qwen3.5-text-0.8B) | bf16 · text-only | Qwen/Qwen3.5-0.8B |
+| [techwithsergiu/Qwen3.5-text-0.8B-bnb-4bit](https://huggingface.co/techwithsergiu/Qwen3.5-text-0.8B-bnb-4bit) | BNB NF4 · text-only | Qwen3.5-text-0.8B |
+| **[techwithsergiu/Qwen3.5-text-0.8B-GGUF](https://huggingface.co/techwithsergiu/Qwen3.5-text-0.8B-GGUF)** | GGUF quants | Qwen3.5-text-0.8B |
+
+The GGUF repo is derived from the text-only f16 model — same weights, different container
+format. `base_model` points to the f16 text variant to keep the VLM and text lineages
+distinct on the Hub.
+
+## Inference
+
+### llama.cpp
+
+```bash
+./llama.cpp/build/bin/llama-cli \
+    -m Qwen3.5-text-0.8B-Q4_K_M.gguf \
+    -p "What is the capital of Romania?" \
+    -n 256
+```
+
+### LM Studio
+
+Load any `.gguf` file from this repo directly in [LM Studio](https://lmstudio.ai).
+Recommended quant: `Q4_K_M`.
+
+### Thinking mode
+
+Qwen3.5 supports an optional chain-of-thought `<think>` block before the answer.
+In the transformers API this is controlled via `enable_thinking=True/False` in
+`apply_chat_template`.
+
+**llama.cpp:** thinking appears to be enabled by default. `--reasoning-budget 0`
+and `--chat-template-kwargs '{"enable_thinking":false}'` have been tested but do
+not reliably disable it — this may be a llama.cpp issue with Qwen3 thinking models.
+Check [llama.cpp issues](https://github.com/ggml-org/llama.cpp/issues) for the
+current status.
+
+## Pipeline diagram
+
+![](diagrams/diagram_02.png)
+
+## Acknowledgements
+
+Based on [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B)
+by the Qwen Team. If you use this model in research, please cite the original:
+
+```bibtex
+@misc{qwen3.5,
+    title  = {{Qwen3.5}: Towards Native Multimodal Agents},
+    author = {{Qwen Team}},
+    month  = {February},
+    year   = {2026},
+    url    = {https://qwen.ai/blog?id=qwen3.5}
+}
+```