Add model card

README.md

@@ -0,0 +1,65 @@
+---
+language:
+- en
+library_name: mlx
+tags:
+- mlx
+- qwen3_5
+- vision-language
+- quantized
+- coder
+base_model: chaddy81/Qwen3.6-27b-coder
+pipeline_tag: image-text-to-text
+---
+
+# chaddy81/Qwen3.6-27b-coder-4bit-mlx
+
+This is a **4-bit** quantized [MLX](https://github.com/ml-explore/mlx) conversion of
+[chaddy81/Qwen3.6-27b-coder](https://huggingface.co/chaddy81/Qwen3.6-27b-coder), for fast local inference on Apple Silicon.
+
+## Details
+
+- **Base model:** [chaddy81/Qwen3.6-27b-coder](https://huggingface.co/chaddy81/Qwen3.6-27b-coder)
+- **Architecture:** `Qwen3_5ForConditionalGeneration` (`qwen3_5`) — vision-language model (text + image + video)
+- **Text backbone:** 64 layers, hidden 5120, 24 attention heads / 4 KV heads (GQA), vocab 248320, context length 262144 (256K)
+- **Vision tower:** 27 layers, hidden 1152
+- **Quantization:** 4-bit, 4.501 bits-per-weight (MLX affine), group size 64
+- **Files:** 3 safetensors shards, ~14 GB
+- **Converted with:** `mlx_lm` 0.31.1, source dtype bfloat16
+
+## Usage
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("chaddy81/Qwen3.6-27b-coder-4bit-mlx")
+prompt = "Write a Python function that returns the nth Fibonacci number."
+messages = [{"role": "user", "content": prompt}]
+text = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
+print(generate(model, tokenizer, prompt=text, max_tokens=512, verbose=True))
+```
+
+Or from the CLI:
+
+```bash
+mlx_lm.generate --model chaddy81/Qwen3.6-27b-coder-4bit-mlx --prompt "Explain async/await in Python."
+```
+
+## Quantization variants
+
+| Variant | bits-per-weight | Size | Repo |
+|---|---|---|---|
+| 8-bit | 8.5 | ~27 GB | [chaddy81/Qwen3.6-27b-coder-8bit-mlx](https://huggingface.co/chaddy81/Qwen3.6-27b-coder-8bit-mlx) |
+| 6-bit | 6.5 | ~20 GB | [chaddy81/Qwen3.6-27b-coder-6bit-mlx](https://huggingface.co/chaddy81/Qwen3.6-27b-coder-6bit-mlx) |
+| 4-bit | 4.5 | ~14 GB | [chaddy81/Qwen3.6-27b-coder-4bit-mlx](https://huggingface.co/chaddy81/Qwen3.6-27b-coder-4bit-mlx) |
+
+## Notes
+
+- Conversion emitted a tokenizer regex warning referencing a Mistral discussion; this is a generic
+  `tokenizers` notice and does not affect the Qwen3.5 architecture or quantized weights. If you observe
+  unexpected tokenization, load the tokenizer with `fix_mistral_regex=True`.
+- License inherited from the base model; refer to [chaddy81/Qwen3.6-27b-coder](https://huggingface.co/chaddy81/Qwen3.6-27b-coder).