Refresh model card

README.md

@@ -14,17 +14,51 @@ tags:
 
 # Qwen3.6-35B-go-v2 4-bit MLX
 
-This is the MLX 4-bit package of the Go-v2 fine-tuned Qwen3.6-35B-A3B model without native MTP tensors.
+A Go-focused Qwen3.6-35B-A3B model for Apple Silicon, packaged in MLX.
 
-It is intended as the plain compatibility sibling for loaders that do not currently accept Qwen3.5 MoE native-MTP weights. The native-MTP sibling is [jedisct1/Qwen3.6-35B-go-v2-MTP-4bit.mlx](https://huggingface.co/jedisct1/Qwen3.6-35B-go-v2-MTP-4bit.mlx).
+Use it as a coding assistant for Go projects: generating focused patches, explaining diffs, tightening tests, reading tool outputs, and making small repo-aware edits. It was tested with [Swival](https://swival.dev) on file-editing and command-running workflows.
 
-## Compatibility
+This is the plain 4-bit compatibility variant. It does not include native MTP tensors, so it is the best starting point if your MLX loader does not support MTP sidecars.
 
-- Native MTP tensors are intentionally removed.
-- The repository name does not include `-MTP`.
-- This package keeps the fine-tuned main model weights, tokenizer files, generation config, and chat template.
-- There are no root LoRA adapter files; this is a standalone MLX artifact.
+## Which Variant Should I Use?
 
-## Source
+- **Use this repo** if you want the smallest plain MLX package or need a loader-friendly non-MTP model.
+- Use [`jedisct1/Qwen3.6-35B-go-v2-8bit.mlx`](https://huggingface.co/jedisct1/Qwen3.6-35B-go-v2-8bit.mlx) if you want more precision without native MTP.
+- Use [`jedisct1/Qwen3.6-35B-go-v2-bf16.mlx`](https://huggingface.co/jedisct1/Qwen3.6-35B-go-v2-bf16.mlx) if you want full precision without native MTP.
+- Use [`jedisct1/Qwen3.6-35B-go-v2-MTP-4bit.mlx`](https://huggingface.co/jedisct1/Qwen3.6-35B-go-v2-MTP-4bit.mlx) if your runtime supports native MTP and you want the faster MTP path.
 
-The artifact was derived from the repaired Go-v2 MLX package by removing `mtp.safetensors`, deleting MTP weight-map entries, and clearing the MTP config fields.
+## Usage
+
+Requires [mlx-lm](https://github.com/ml-explore/mlx-examples/tree/main/llms/mlx_lm):
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("jedisct1/Qwen3.6-35B-go-v2-4bit.mlx")
+
+messages = [
+    {"role": "system", "content": "You are an expert Go developer."},
+    {"role": "user", "content": "Generate a focused patch that replaces the manual retry loop in fetchUser() with the shared retry helper."},
+]
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+response = generate(model, tokenizer, prompt=prompt, max_tokens=500)
+print(response)
+```
+
+## What It Is Good At
+
+- Writing idiomatic Go patches from a concise change request.
+- Explaining Go diffs in commit-message style.
+- Following tool-calling workflows where it needs to inspect files before editing.
+- Keeping changes focused instead of turning small fixes into broad rewrites.
+- Working with tests, command output, and repository context.
+
+## Limitations
+
+- Outputs should be reviewed before use, especially patches that touch production systems.
+- The model works best on focused Go changes, tests, and explanations. Very large refactors may need to be split into smaller steps.
+- Tool calling depends on the runtime and client preserving the chat template and tool schema format.