QW

Qwen3.5-35B-A3B

QwenGGUF by janhqUpdated 2026-02-25
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant12.0 GB
Quick answer

Qwen3.5-35B-A3B needs about 21.0 GB of memory at Q4_0 (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 13 quants, from 12.0 GB (IQ2_XXS) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.5-35B-A3B – 34.7B parameter multimodal LLM

Qwen3.5-35B-A3B is a 34.7B parameter model with a 262144 token context window. It supports reasoning, tools, and vision. The model is released under the apache-2.0 license.

Good at

  • Reasoning
  • Tool use
  • Vision tasks

Limits

  • Large context requires high VRAM
  • No native vision support in llama.cpp
  • Requires 8k context for memory estimates

Best for

  • Complex reasoning workflows
  • Multimodal content generation
  • Tool‑enabled automation

Who it’s for. Developers needing a large, multimodal model for advanced reasoning and tool integration. Researchers working on vision‑language tasks can also benefit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS12.0 GB 13.2 GB
Too big Get file →
IQ2_M12.6 GB 13.8 GB
Too big Get file →
Q2_K12.9 GB 14.1 GB
Too big Get file →
Q2_K_L13.0 GB 14.2 GB
Too big Get file →
Q3_K_S15.2 GB 16.4 GB
Too big Get file →
Q3_K_M16.8 GB 18.0 GB
Too big Get file →
Q4_019.8 GB 21.0 GB
Too big Get file →
Q4_K_S19.9 GB 21.1 GB
Too big Get file →
Q4_121.9 GB 23.0 GB
Too big Get file →
Q5_K_S24.0 GB 25.2 GB
Too big Get file →
Q5_K_M24.8 GB 26.0 GB
Too big Get file →
Q6_K28.6 GB 29.8 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →

For 8 GB VRAM use IQ2_XXS (12.03 GB file, 13.2 GB memory). For 16 GB VRAM use Q3_K_S (15.23 GB file, 16.4 GB memory). For 32 GB VRAM use Q5_K_M (24.81 GB file, 26 GB memory). Estimates are approximate.

What GPU do you need for Qwen3.5-35B-A3B?

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: the best quant that fits is Q2_K_L (13.0 GB file, about 14.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (21.9 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.6 GB file, about 29.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).

Which Qwen3.5-35B-A3B quant should you choose?

Q4_0 (19.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ2_XXS at 12.0 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

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized byjanhq
FamilyQwen
Licenseapache-2.0
Downloads (HF)948
Last updated2026-02-25

Frequently asked questions about Qwen3.5-35B-A3B

How much VRAM does Qwen3.5-35B-A3B need?

About 21.0 GB at Q4_0 with an 8K context window. That is the 19.8 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 Qwen3.5-35B-A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.5-35B-A3B GGUF?

It depends on the quant: IQ2_XXS is 12.0 GB, IQ2_M is 12.6 GB, Q2_K is 12.9 GB, Q2_K_L is 13.0 GB, Q3_K_S is 15.2 GB, Q3_K_M is 16.8 GB and 7 more.

What context length does Qwen3.5-35B-A3B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Qwen3.5-35B-A3B GGUF?

The files are on Hugging Face in the janhq/Qwen3.5-35B-A3B-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 Qwen3.5-35B-A3B 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 Qwen3.5-35B-A3B on 8 GB VRAM?

Use the IQ2_XXS quantized model; it requires about 13.2 GB memory at 8k context, which is close to 8 GB VRAM but may need swap.

Does this model support vision in llama.cpp?

The model has vision ability but llama.cpp does not natively support vision; additional tooling is required.

What license applies to this model?

The model is licensed under apache-2.0.

Other GGUFs of Qwen3.5-35B-A3B

Similar models

Browse all →

More from janhq

All by janhq →

More Qwen models

All Qwen →

Other large models

All large models →