Qwen3.6 35B A3B NVFP4 Src needs about 21.0 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 19.8 GB (Q4_K_M) to 23.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.6 35B A3B NVFP4 – a vision‑enabled MoE language model
Qwen3.6 35B A3B NVFP4 is a causal language model with a vision encoder. It contains 35B total parameters and activates 3B per token. The model supports a native context length of 262,144 tokens and can be extended up to 1,010,000 tokens.
Good at
- Vision‑enabled text generation
- Large‑context reasoning
- Agentic coding tasks
Limits
- Requires 8,000‑token context for memory estimates
- No native vision support beyond the encoder
- Apache‑2.0 license restricts commercial redistribution
Best for
- Developing autonomous agents
- Extending context for long documents
- Vision‑augmented coding assistants
Who it’s for. Engineers and researchers building applications that need both language and vision capabilities in a single model. The model is suitable for developers who can manage the memory requirements of a MoE architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 19.8 GB | 21.0 GB | Too big | Get file → | |
| Q8_0 | 20.8 GB | 22.0 GB | Too big | Get file → | |
| BF16 | 23.1 GB | 24.2 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K_M quantization (file size 19.78 GB, estimated 21 GB memory at 8k context). For 12 GB VRAM, Q8_0 (20.8 GB, 22 GB memory) is a good balance. If you have 16 GB or more, BF16 (23.07 GB, 24.2 GB memory) offers the highest precision.
What GPU do you need for Qwen3.6 35B A3B NVFP4 Src?
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: the best quant that fits is Q8_0 (20.8 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (23.1 GB file, about 24.2 GB in use).
Which Qwen3.6 35B A3B NVFP4 Src quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6 35B A3B NVFP4 Src: it balances file size and quality well. Here it is a 19.8 GB file.
The Q8_0 file is 20.8 GB, about 1.1 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.6 35B A3B NVFP4 Src
How much VRAM does Qwen3.6 35B A3B NVFP4 Src need?
About 21.0 GB at Q4_K_M with an 8K context window. That is the 19.8 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 NVFP4 Src on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.6 35B A3B NVFP4 Src GGUF?
It depends on the quant: Q4_K_M is 19.8 GB, Q8_0 is 20.8 GB, BF16 is 23.1 GB.
What context length does Qwen3.6 35B A3B NVFP4 Src 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 2.7 GB at 32K.
Where can I download Qwen3.6 35B A3B NVFP4 Src GGUF?
The files are on Hugging Face in the LibertAIDAI/Qwen3.6-35B-A3B-NVFP4-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 NVFP4 Src 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?
Yes, using the Q4_K_M quantization which estimates 21 GB memory at 8k context, but you will need to reduce context or batch size.
Does this model support vision tasks?
Yes, it includes a vision encoder and has detected vision abilities.
What license applies to this model?
The model is released under the apache-2.0 license.