Qwen3.6 35B A3B needs about 26.2 GB of memory at MXFP4_MOE (a 23.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 21.2 GB (MXFP4_MOE) to 23.0 GB (MXFP4_MOE).
Qwen3.6 35B A3B – large‑scale causal language model with MoE
Qwen3.6 35B A3B is a 35.5B parameter causal language model with 3B active parameters. It supports a native context length of 262,144 tokens and can be extended up to 1,010,000 tokens. The model is released under the apache-2.0 license.
Good at
- Agentic coding workflows
- Frontend and repository reasoning
- Iterative development with context preservation
Limits
- No vision support
- Requires large VRAM for full precision
- Limited to 262,144 native context length
Best for
- Developing coding assistants
- Building repository‑level reasoning tools
- Iterative code generation projects
Who it’s for. Engineers and researchers building advanced coding assistants or repository‑level reasoning systems. The model is suitable for teams needing large context and MoE efficiency.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 21.2 GB | 24.2 GB | Too big | Get file → | |
| MXFP4_MOE | 23.0 GB | 26.2 GB | Too big | Get file → | |
| MXFP4_MOE | 23.0 GB | 26.2 GB | Too big | Get file → |
For 8 GB VRAM, use the MXFP4_MOE quantization; the 21.16 GB file requires about 24.2 GB of VRAM at 8 k context. For 12 GB VRAM, the 22.96 GB file needs about 26.2 GB of VRAM. Memory estimates are approximate.
What GPU do you need for Qwen3.6 35B A3B?
These figures add the file size, an fp16 KV cache at an 8K context window 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 MXFP4_MOE (23.0 GB file, about 26.2 GB in use).
Which Qwen3.6 35B A3B quant should you choose?
MXFP4_MOE (23.0 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is MXFP4_MOE at 21.2 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.6 35B A3B
How much VRAM does Qwen3.6 35B A3B need?
About 26.2 GB at MXFP4_MOE with an 8K context window. That is the 23.0 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.6 35B A3B GGUF?
It depends on the quant: MXFP4_MOE is 21.2 GB, MXFP4_MOE is 23.0 GB, MXFP4_MOE is 23.0 GB.
What context length does Qwen3.6 35B A3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Qwen3.6 35B A3B GGUF?
The files are on Hugging Face in the noctrex/Qwen3.6-35B-A3B-MTP-MXFP4_MOE-GGUF 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 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 Qwen3.6 35B A3B on 8 GB VRAM?
The MXFP4_MOE quantization requires approximately 24.2 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does the model support vision tasks?
No, the model is a causal language model with no vision encoder.
What license applies to this model?
The model is released under the apache-2.0 license.