Qwen3.6 35B A3B NVFP4 MTP needs about 25.0 GB of memory at its main file (a 23.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 22.9 GB to 26.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Qwen3.6 35B A3B NVFP4 MTP – large MoE language model in GGUF format
Qwen3.6 35B A3B NVFP4 MTP is a 35.5B parameter transformer with 3B active experts. It supports up to 262,144 token context and is released under Apache‑2.0. The model is ready for commercial and non‑commercial use.
Good at
- Reasoning
- Tool use
- Long‑context handling
Limits
- No vision support in GGUF
- Large VRAM requirement
- Mixture‑of‑Experts complexity
Best for
- AI agent systems
- Chatbots
- RAG pipelines
Who it’s for. Developers who need a pre‑quantized, large‑scale language model for deployment in AI agents, chatbots, or retrieval‑augmented generation. The model is suitable for both commercial and non‑commercial projects under Apache‑2.0.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 22.9 GB | 24.1 GB | Too big | Get file → | |
| — | 23.9 GB | 25.0 GB | Too big | Get file → | |
| — | 26.1 GB | 27.3 GB | Too big | Get file → |
For 8‑GB VRAM use the 22.91 GB file; it estimates 24.1 GB RAM at 8K context. For 12‑GB VRAM use the 23.85 GB file; it estimates 25 GB RAM. For 16‑GB VRAM use the 26.14 GB file; it estimates 27.3 GB RAM. Estimates are approximate.
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: 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 the main file (26.1 GB file, about 27.3 GB in use).
Which Qwen3.6 35B A3B NVFP4 MTP quant should you choose?
If memory is tight, the smallest file is the first one in the table at 22.9 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 25.0 GB at its main file 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 NVFP4 MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.6 35B A3B NVFP4 MTP GGUF?
It depends on the quant: file is 22.9 GB, file is 23.9 GB, file is 26.1 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 2.8 GB at 32K.
Where can I download Qwen3.6 35B A3B NVFP4 MTP GGUF?
The files are on Hugging Face in the neko-legends/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 this model on 8 GB VRAM?
The 22.91 GB file estimates 24.1 GB RAM at 8K context, so 8 GB VRAM is insufficient. Use a larger GPU or a smaller quant.
Does the model support image input?
The GGUF version does not include vision support; only text is supported.
What license applies?
The model is released under Apache‑2.0, allowing commercial and non‑commercial use.