Qwen3.5 397B A17B needs about 136.9 GB of memory at IQ2_XS (a 121.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 1.1 GB (BF16) to 208.4 GB.
Qwen3.5 397B A17B is a 396B-parameter Qwen model in GGUF format, quantized by ubergarm. Its trained context length is 256K tokens. The repository has 7 quant files, from 1.1 GB (BF16) to 208.4 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 1.1 GB | 1.8 GB | Fits | Get file → | |
| — | 95.4 GB (3 parts) | 107.3 GB | Too big | Get file → | |
| — | 116.1 GB (4 parts) | 130.6 GB | Too big | Get file → | |
| IQ2_XS | 121.8 GB (4 parts) | 136.9 GB | Too big | Get file → | |
| — | 148.3 GB (4 parts) | 166.6 GB | Too big | Get file → | |
| Q3_K | 193.3 GB (5 parts) | 216.9 GB | Too big | Get file → | |
| — | 208.4 GB (6 parts) | 233.9 GB | Too big | Get file → |
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 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: the best quant that fits is BF16 (1.1 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (1.1 GB file, about 1.8 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (1.1 GB file, about 1.8 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (1.1 GB file, about 1.8 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (1.1 GB file, about 1.8 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (1.1 GB file, about 1.8 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (1.1 GB file, about 1.8 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (1.1 GB file, about 1.8 GB in use).
Which Qwen3.5 397B A17B quant should you choose?
IQ2_XS (121.8 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is BF16 at 1.1 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
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 136.9 GB at IQ2_XS with an 8K context window. That is the 121.8 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 Qwen3.5 397B A17B on an 8 GB GPU?
Yes, with BF16: the 1.1 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.5 397B A17B GGUF?
It depends on the quant: BF16 is 1.1 GB, file is 95.4 GB, file is 116.1 GB, IQ2_XS is 121.8 GB, file is 148.3 GB, Q3_K is 193.3 GB and 1 more.
What context length does Qwen3.5 397B A17B support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Qwen3.5 397B A17B GGUF?
The files are on Hugging Face in the ubergarm/Qwen3.5-397B-A17B-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.