QW

Qwen3.5 397B A17B heretic GGUF v2 MTP

QwenGGUF by dxx117Updated 2026-05-22
Download on Hugging Face
Parameters403B
Context256K
Layers—
Architectureqwen35moe
Smallest quant161.4 GB
Quick answer

Qwen3.5 397B A17B heretic GGUF v2 MTP needs about 275.6 GB of memory at Q4_K_M (a 245.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 161.4 GB (IQ3_XXS) to 249.4 GB (Q4_K_M).

Qwen3.5 397B A17B heretic GGUF v2 MTP is a 403B-parameter Qwen model in GGUF format, quantized by dxx117. Its trained context length is 256K tokens. The repository has 8 quant files, from 161.4 GB (IQ3_XXS) to 249.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS161.4 GB (4 parts) 181.2 GB
Too big Get file →
IQ3_XXS165.2 GB (4 parts) 185.5 GB
Too big Get file →
Q3_K196.4 GB (4 parts) 220.5 GB
Too big Get file →
Q3_K200.3 GB (5 parts) 224.8 GB
Too big Get file →
IQ4_XS219.6 GB (5 parts) 246.5 GB
Too big Get file →
IQ4_XS223.4 GB (5 parts) 250.8 GB
Too big Get file →
Q4_K_M245.6 GB (5 parts) 275.6 GB
Too big Get file →
Q4_K_M249.4 GB (6 parts) 279.9 GB
Too big Get file →

What GPU do you need for Qwen3.5 397B A17B heretic GGUF v2 MTP?

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: 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 GGUF v2 MTP quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 397B A17B heretic GGUF v2 MTP: it balances file size and quality well. Here it is a 245.6 GB file.

If memory is tight, the smallest file is IQ3_XXS at 161.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters403B (approximate, mixture of experts)
Active parameters17B
Trained context262,144 tokens

Source

Quantized bydxx117
FamilyQwen
Licenseapache-2.0
Downloads (HF)103
Last updated2026-05-22

Frequently asked questions about Qwen3.5 397B A17B heretic GGUF v2 MTP

How much VRAM does Qwen3.5 397B A17B heretic GGUF v2 MTP need?

About 275.6 GB at Q4_K_M with an 8K context window. That is the 245.6 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 GGUF v2 MTP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 181.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.5 397B A17B heretic GGUF v2 MTP GGUF?

It depends on the quant: IQ3_XXS is 161.4 GB, IQ3_XXS is 165.2 GB, Q3_K is 196.4 GB, Q3_K is 200.3 GB, IQ4_XS is 219.6 GB, IQ4_XS is 223.4 GB and 2 more.

What context length does Qwen3.5 397B A17B heretic GGUF v2 MTP support?

The GGUF header lists a trained context length of 262,144 tokens (256K).

Where can I download Qwen3.5 397B A17B heretic GGUF v2 MTP GGUF?

The files are on Hugging Face in the dxx117/Qwen3.5-397B-A17B-heretic-GGUF-v2-MTP 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 GGUF v2 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.

Similar models

Browse all →

More from dxx117

All by dxx117 →

More Qwen models

All Qwen →

Other large models

All large models →