QW

Qwen3.5 397B A17B

QwenGGUF by bartowskiUpdated 2026-05-21
Download on Hugging Face
Parameters403B
Context256K
Layers61
Architectureqwen35moe
Smallest quant1.1 GB
Quick answer

Qwen3.5 397B A17B needs about 249.8 GB of memory at Q4_K_M (a 248.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 31 quants, from 1.1 GB to 428.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.1 GB.

Qwen3.5 397B A17B – a large multimodal LLM with 17B active experts

Qwen3.5 397B A17B is a 397 billion‑parameter model with 17 billion active mixture‑of‑expert parameters. It supports vision and text, trained on 262,144‑token context. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Vision‑language tasks
  • Large‑context reasoning
  • Multilingual generation

Limits

  • Requires large VRAM for full precision
  • No built‑in vision support in llama.cpp
  • Limited to 262,144‑token context

Best for

  • Multimodal content creation
  • Long‑form document analysis
  • Cross‑lingual translation

Who it’s for. Developers needing a powerful vision‑language model for research or production. The model is suitable for teams with access to high‑end GPUs or large‑memory inference setups.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.1 GB 2.7 GB
Fits Get file →
Q4_05.1 GB 6.7 GB
Fits Get file →
Q8_09.2 GB 10.7 GB
Too big Get file →
IQ1_S88.7 GB (3 parts) 90.3 GB
Too big Get file →
IQ1_M98.3 GB (3 parts) 99.8 GB
Too big Get file →
IQ2_XXS113.3 GB (3 parts) 114.8 GB
Too big Get file →
IQ2_XS125.4 GB (4 parts) 126.9 GB
Too big Get file →
IQ2_S127.3 GB (4 parts) 128.8 GB
Too big Get file →
IQ2_M139.9 GB (4 parts) 141.4 GB
Too big Get file →
Q2_K146.3 GB (4 parts) 147.8 GB
Too big Get file →
Q2_K_L147.3 GB (4 parts) 148.8 GB
Too big Get file →
IQ3_XXS172.7 GB (5 parts) 174.2 GB
Too big Get file →
Q3_K_S179.9 GB (5 parts) 181.5 GB
Too big Get file →
IQ3_XS188.2 GB (5 parts) 189.7 GB
Too big Get file →
Q3_K_M188.2 GB (5 parts) 189.7 GB
Too big Get file →
Q3_K_L195.9 GB (5 parts) 197.5 GB
Too big Get file →
IQ3_M196.0 GB (5 parts) 197.5 GB
Too big Get file →
Q3_K_XL196.8 GB (5 parts) 198.3 GB
Too big Get file →
IQ4_XS219.2 GB (6 parts) 220.8 GB
Too big Get file →
IQ4_NL231.5 GB (6 parts) 233.0 GB
Too big Get file →
Q4_0232.4 GB (6 parts) 234.0 GB
Too big Get file →
Q4_K_S239.6 GB (7 parts) 241.1 GB
Too big Get file →
Q4_K_M248.3 GB (7 parts) 249.8 GB
Too big Get file →
Q4_K_L249.0 GB (7 parts) 250.5 GB
Too big Get file →
Q4_1256.1 GB (7 parts) 257.6 GB
Too big Get file →
Q5_K_S281.0 GB (8 parts) 282.5 GB
Too big Get file →
Q5_K_M290.0 GB (8 parts) 291.5 GB
Too big Get file →
Q5_K_L290.6 GB (8 parts) 292.1 GB
Too big Get file →
Q6_K348.9 GB (9 parts) 350.4 GB
Too big Get file →
Q6_K_L349.4 GB (9 parts) 350.9 GB
Too big Get file →
Q8_0428.6 GB (11 parts) 430.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (6.7 GB memory at 8k context). With 16 GB VRAM, Q8_0 (10.7 GB) or Q4_K_L (250.5 GB memory estimate) are viable. For 32 GB VRAM, Q5_K_M (291.5 GB) or Q6_K (350.4 GB) provide higher quality. 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: the best quant that fits is the main file (1.1 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_0 (5.1 GB file, about 6.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.2 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.2 GB file, about 10.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (9.2 GB file, about 10.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (9.2 GB file, about 10.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (9.2 GB file, about 10.7 GB in use).

Which Qwen3.5 397B A17B quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 397B A17B: it balances file size and quality well. Here it is a 248.3 GB file.

The Q8_0 file is 9.2 GB, about 0.0 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 1.1 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

Architectureqwen35moe
Parameters403B (approximate, mixture of experts)
Active parameters17B
Layers61
Trained context262,144 tokens
KV cache (fp16)122 KB per token

Source

Quantized bybartowski
FamilyQwen
Licenseapache-2.0
Downloads (HF)8,911
Last updated2026-05-21

Frequently asked questions about Qwen3.5 397B A17B

How much VRAM does Qwen3.5 397B A17B need?

About 249.8 GB at Q4_K_M with an 8K context window. That is the 248.3 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 Q4_0: the 5.1 GB file needs about 6.7 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: file is 1.1 GB, Q4_0 is 5.1 GB, Q8_0 is 9.2 GB, IQ1_S is 88.7 GB, IQ1_M is 98.3 GB, IQ2_XXS is 113.3 GB and 25 more.

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 4.1 GB at 32K.

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

The files are on Hugging Face in the bartowski/Qwen_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.

Can I run Qwen3.5 397B A17B on 8 GB VRAM?

Use the Q4_0 quantization; it requires about 6.7 GB of VRAM at 8k context.

Does this model support vision tasks in llama.cpp?

The model has vision capability, but llama.cpp does not natively support vision inference for this model.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.5-397B-A17B

Similar models

Browse all →

More from bartowski

All by bartowski →

More Qwen models

All Qwen →

Other large models

All large models →