RedHatAI/Qwen3.6-35B-A3B-NVFP4 needs about 23.7 GB of memory at its main file (a 22.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
RedHatAI/Qwen3.6-35B-A3B-NVFP4 – a 35B multimodal MoE model in GGUF format
Qwen3.6-35B-A3B-NVFP4 is a 34.7 billion‑parameter mixture‑of‑experts model with 256 experts, 8 active per token. It supports reasoning, tools, and vision, and was quantized with NVFP4 compressed‑tensors for use with llama.cpp.
Good at
- Multimodal reasoning
- Tool usage
- Vision tasks
Limits
- Requires ~23.7 GB VRAM at 8 k context
- Large context size 262144 tokens
- Apache‑2.0 license
Best for
- Research on multimodal LLMs
- Developing vision‑enabled assistants
- Testing MoE architectures
Who it’s for. Researchers and developers needing a large multimodal model with mixture‑of‑experts architecture. The model is suitable for environments that can provide the necessary VRAM and support NVFP4 quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 22.5 GB | 23.7 GB | Too big | Get file → |
The only available GGUF file is the NVFP4 quantized version, 22.5 GB in size. It requires approximately 23.7 GB of VRAM at 8 k context. Use this quant if your GPU has at least 24 GB VRAM; otherwise the model cannot be loaded.
What GPU do you need for RedHatAI/Qwen3.6-35B-A3B-NVFP4?
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 the main file (22.5 GB file, about 23.7 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about RedHatAI/Qwen3.6-35B-A3B-NVFP4
How much VRAM does RedHatAI/Qwen3.6-35B-A3B-NVFP4 need?
About 23.7 GB at its main file with an 8K context window. That is the 22.5 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 RedHatAI/Qwen3.6-35B-A3B-NVFP4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 23.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of RedHatAI/Qwen3.6-35B-A3B-NVFP4 GGUF?
It depends on the quant: file is 22.5 GB.
What context length does RedHatAI/Qwen3.6-35B-A3B-NVFP4 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 RedHatAI/Qwen3.6-35B-A3B-NVFP4 GGUF?
The files are on Hugging Face in the knoopx/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 RedHatAI/Qwen3.6-35B-A3B-NVFP4 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?
No. The model requires about 23.7 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does it support vision tasks?
Yes. The model includes a Qwen2.5‑VL‑style vision encoder merged into the language model.
Is it a mixture‑of‑experts model?
Yes, it has 256 experts with 8 active per token, using grouped‑query MoE.