Qwen3.5 397B A17B heretic needs about 207.6 GB of memory at Q3_K_L (a 206.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 130.5 GB (IQ2_M) to 241.4 GB (Q4_K_L). Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.
Qwen3.5 397B A17B heretic is a 396B-parameter Qwen model in GGUF format, quantized by dxx117. Its trained context length is 256K tokens. The repository has 5 quant files, from 130.5 GB (IQ2_M) to 241.4 GB (Q4_K_L).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 130.5 GB (17 parts) | 132.0 GB | Too big | Get file → | |
| IQ3_XXS | 154.0 GB (17 parts) | 155.5 GB | Too big | Get file → | |
| Q3_K_L | 206.1 GB (17 parts) | 207.6 GB | Too big | Get file → | |
| IQ4_XS | 212.5 GB (17 parts) | 214.0 GB | Too big | Get file → | |
| Q4_K_L | 241.4 GB (17 parts) | 242.9 GB | Too big | Get file → |
What GPU do you need for Qwen3.5 397B A17B heretic?
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 heretic quant should you choose?
Q3_K_L (206.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ2_M at 130.5 GB, with the quality trade-offs that come with fewer bits. 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.5 397B A17B heretic
How much VRAM does Qwen3.5 397B A17B heretic need?
About 207.6 GB at Q3_K_L with an 8K context window. That is the 206.1 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 heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 132.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.5 397B A17B heretic GGUF?
It depends on the quant: IQ2_M is 130.5 GB, IQ3_XXS is 154.0 GB, Q3_K_L is 206.1 GB, IQ4_XS is 212.5 GB, Q4_K_L is 241.4 GB.
What context length does Qwen3.5 397B A17B heretic 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 heretic GGUF?
The files are on Hugging Face in the dxx117/Qwen3.5-397B-A17B-heretic-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 heretic 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.