Qwen3.5-397B-A17B needs about 244.2 GB of memory at its main file (a 242.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 186.9 GB to 288.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.
Qwen3.5-397B-A17B – 397B parameter MoE model with vision support
Qwen3.5-397B-A17B is a causal language model with a built‑in vision encoder. It contains 397B total parameters, with 17B active per token. The model supports a 262,144 token context length and is licensed under apache-2.0.
Good at
- Vision‑language tasks
- Large‑context reasoning
- Multilingual generation
Limits
- Requires >200 GB VRAM for full precision
- No official benchmark scores yet
- Only vision support, no audio
Best for
- Multimodal chatbots
- Long‑form document analysis
- AI agents with tool use
Who it’s for. Developers needing a large multimodal foundation model for research or production. The model is suitable for teams with access to high‑end GPUs or cloud inference services.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 186.9 GB | 188.4 GB | Too big | Get file → | |
| — | 242.7 GB | 244.2 GB | Too big | Get file → | |
| — | 288.5 GB | 290.0 GB | Too big | Get file → |
For 8 GB VRAM use the 186.91 GB file; it estimates 188.4 GB memory at 8 k context. For 16 GB VRAM use the 242.68 GB file; it estimates 244.2 GB memory. For 32 GB VRAM use the 288.52 GB file; it estimates 290 GB memory. These estimates are approximate.
What GPU do you need for Qwen3.5-397B-A17B?
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: no quant fits at an 8K context.
Which Qwen3.5-397B-A17B quant should you choose?
If memory is tight, the smallest file is the first one in the table at 186.9 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 Qwen3.5-397B-A17B
How much VRAM does Qwen3.5-397B-A17B need?
About 244.2 GB at its main file with an 8K context window. That is the 242.7 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 Qwen3.5-397B-A17B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 188.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.5-397B-A17B GGUF?
It depends on the quant: file is 186.9 GB, file is 242.7 GB, file is 288.5 GB.
What context length does Qwen3.5-397B-A17B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.0 GB at 8K and 4.0 GB at 32K.
Where can I download Qwen3.5-397B-A17B GGUF?
The files are on Hugging Face in the mudler/Qwen3.5-397B-A17B-APEX-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 Qwen3.5-397B-A17B 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 Qwen3.5-397B-A17B on 8 GB VRAM?
The 186.91 GB GGUF file estimates 188.4 GB memory at 8 k context, which exceeds 8 GB VRAM. It cannot run on 8 GB VRAM without further quantization.
Does the model support vision?
Yes, it includes a built‑in vision encoder (mmproj).