Qwen3.6 35B A3B mlx claude coder abliterated needs about 29.8 GB of memory at Q4_K_M (a 23.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 21.5 GB.
Qwen3.6 35B A3B mlx claude coder abliterated – local coding agent
This model is a 36 billion‑parameter Qwen3.6 variant with 3 billion active mixture‑of‑experts parameters. It is tuned for coding, reasoning, and tool use, and speaks the Anthropic‑compatible API for Claude Code. The context length is 262 144 tokens.
Good at
- Coding with function calling
- Reasoning tasks
- Tool integration
Limits
- Large VRAM requirement – 29.8 GB at 8 k context
- No vision support
- Requires Apache‑2.0 license compliance
Best for
- Local Claude Code execution
- Agentic code editing
- Sysadmin automation
Who it’s for. Developers and researchers who need a fully local, low‑cost coding assistant that can invoke tools and write files directly. It is suitable for controlled environments and research use, not for public or production deployments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 23.9 GB | 29.8 GB | Too big | Get file → |
The only available quant is Q4_K_M with a file size of 23.94 GB. It requires approximately 29.8 GB of VRAM at 8 k context. For lower memory budgets, no other quant is available.
What GPU do you need for Qwen3.6 35B A3B mlx claude coder abliterated?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_K_M (23.9 GB file, about 29.8 GB in use).
Which Qwen3.6 35B A3B mlx claude coder abliterated quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6 35B A3B mlx claude coder abliterated: it balances file size and quality well. Here it is a 23.9 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Qwen3.6 35B A3B mlx claude coder abliterated
How much VRAM does Qwen3.6 35B A3B mlx claude coder abliterated need?
About 29.8 GB at Q4_K_M with an 8K context window. That is the 23.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Qwen3.6 35B A3B mlx claude coder abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.6 35B A3B mlx claude coder abliterated GGUF?
It depends on the quant: Q4_K_M is 23.9 GB.
What context length does Qwen3.6 35B A3B mlx claude coder abliterated support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 5.4 GB at 8K and 21.5 GB at 32K.
Where can I download Qwen3.6 35B A3B mlx claude coder abliterated GGUF?
The files are on Hugging Face in the rafw007/Qwen3.6-35B-A3B-mlx-claude-coder-abliterated repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwen3.6 35B A3B mlx claude coder abliterated use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
No. The Q4_K_M quant requires about 29.8 GB of VRAM at 8 k context, which exceeds 8 GB.
Does it support vision?
No, the model has no vision capabilities.
Is it safe for public use?
It has reduced safety filtering; use only in controlled or research settings.