Qwen3.6 35B A3B needs about 39.0 GB of memory at Q8_0 (a 37.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 37.8 GB (Q8_0) to 71.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Qwen3.6 35B A3B – a vision‑enabled, mixture‑of‑experts language model
Qwen3.6 35B A3B is a causal language model with a vision encoder, built on the Qwen3.6 architecture. It contains 35B total parameters with 3B active experts and supports up to 262144 context tokens.
Good at
- Vision‑enabled text generation
- Agentic coding workflows
- Large context reasoning
Limits
- Requires 39GB VRAM for Q8_0 at 8k context
- No support for non‑vision tasks only
- Apache‑2.0 license limits commercial use without attribution
Best for
- Developers building AI agents with visual input
- Large‑scale content generation with long context
- Research on mixture‑of‑experts models
Who it’s for. This model is intended for developers and researchers who need a robust, vision‑capable language model with extensive context handling. It is suitable for building AI agents and conducting advanced NLP experiments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 37.8 GB | 39.0 GB | Too big | Get file → | |
| BF16 | 71.1 GB | 72.3 GB | Too big | Get file → |
For a GPU with 40GB VRAM, use the Q8_0 quantization (file size 37.8GB, estimated memory 39GB). If you have 80GB VRAM, the BF16 quantization (file size 71.07GB, estimated memory 72.3GB) is available. 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 (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: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).
Which Qwen3.6 35B A3B quant should you choose?
Q8_0 (37.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
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 39.0 GB at Q8_0 with an 8K context window. That is the 37.8 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 39.0 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: Q8_0 is 37.8 GB, BF16 is 71.1 GB.
What context length does Qwen3.6 35B A3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download Qwen3.6 35B A3B GGUF?
The files are on Hugging Face in the ggml-org/Qwen3.6-35B-A3B-MTP-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 8GB VRAM?
No, the smallest quantization requires at least 39GB VRAM at 8k context.
Does this model support vision tasks?
Yes, it includes a vision encoder and can process visual input.
What license applies to this model?
The model is released under the Apache‑2.0 license.