Qwen3.6 35B A3B NVFP4 MTP 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 4 quants, from 3.7 GB 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 MTP – a vision‑enabled MoE language model
Qwen3.6 35B A3B NVFP4 MTP is a causal language model with a vision encoder. It contains 35B total parameters and 3B active parameters. 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 handling
- Multi‑token prediction for speculative decoding
Limits
- No vision support in llama.cpp without NVFP4
- Requires 32 GB VRAM for full performance
- License is apache‑2.0
Best for
- Vision‑based chatbots
- Long‑form content creation
- Agentic coding assistants
Who it’s for. Developers building applications that need both vision and language understanding with a large context window. The model is suitable for research and production use where the apache‑2.0 license is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.7 GB | 4.9 GB | Fits | Get file → | |
| 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 Q4_K_M (file size 19.78 GB, memory 21 GB at 8 k context). For 16 GB VRAM, Q8_0 (20.8 GB, 22 GB). BF16 offers the largest precision but needs 24.2 GB memory. The unknown quant is 3.74 GB but memory is 4.9 GB, suitable for very low‑budget setups.
What GPU do you need for Qwen3.6 35B A3B NVFP4 MTP?
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: the best quant that fits is the main file (3.7 GB file, about 4.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (3.7 GB file, about 4.9 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (3.7 GB file, about 4.9 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (3.7 GB file, about 4.9 GB in use).
- 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 MTP quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6 35B A3B NVFP4 MTP: 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.
If memory is tight, the smallest file is the first one in the table at 3.7 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.6 35B A3B NVFP4 MTP
How much VRAM does Qwen3.6 35B A3B NVFP4 MTP 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 MTP on an 8 GB GPU?
Yes, with the smaller files: the 3.7 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.6 35B A3B NVFP4 MTP GGUF?
It depends on the quant: file is 3.7 GB, 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 MTP 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 MTP GGUF?
The files are on Hugging Face in the LibertAIDAI/Qwen3.6-35B-A3B-NVFP4-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 NVFP4 MTP 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 NVFP4 MTP on 8 GB VRAM?
The Q4_K_M quant requires about 21 GB memory at 8 k context, so 8 GB VRAM is insufficient for full inference.
Does this model support vision tasks in llama.cpp?
Vision support is available only with NVFP4 quantizations; standard llama.cpp builds without NVFP4 do not include vision.
What is the context length of this model?
The native context length is 262,144 tokens, extendable up to 1,010,000 tokens with appropriate configuration.