QW

Qwen3.6 35B A3B

QwenGGUF by byteshapeUpdated 2026-05-20
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant10.0 GB
Quick answer

Qwen3.6 35B A3B needs about 16.9 GB of memory at IQ4_XS (a 15.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 10.0 GB (IQ2_S) to 18.6 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Qwen3.6 35B A3B – Vision‑capable, 35B parameter LLM with MTP support

Qwen3.6 35B A3B is a 35B parameter causal language model with vision encoder. It supports a native context length of 262,144 tokens and can be extended up to 1,010,000 tokens. The model is quantized for GPU‑only inference and includes Multi‑Token Prediction (MTP).

Good at

  • Vision‑enabled text generation
  • Large context handling
  • MTP‑accelerated decoding

Limits

  • Requires recent llama.cpp build for MTP
  • Large VRAM needed for higher‑bit quants
  • No explicit language support listed

Best for

  • Vision‑augmented coding assistants
  • Long‑form document analysis
  • MTP‑based rapid inference

Who it’s for. Developers building vision‑enabled AI assistants or code generation tools that need large context and fast decoding. Suitable for GPU‑only inference setups with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_S10.0 GB 11.2 GB
Too big Get file →
IQ3_S13.6 GB 14.8 GB
Too big Get file →
IQ4_XS15.7 GB 16.9 GB
Too big Get file →
IQ4_XS17.6 GB 18.8 GB
Too big Get file →
IQ4_XS18.6 GB 19.8 GB
Too big Get file →

For 8 GB VRAM, use IQ2_S (10.02 GB, ~11.2 GB memory at 8 k context). For 12 GB VRAM, IQ3_S (13.61 GB, ~14.8 GB memory). For 16 GB VRAM, IQ4_XS (15.67 GB, ~16.9 GB memory). Memory estimates are approximate.

What GPU do you need for Qwen3.6 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: the best quant that fits is IQ2_S (10.0 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_S (13.6 GB file, about 14.8 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (18.6 GB file, about 19.8 GB in use).

Which Qwen3.6 35B A3B quant should you choose?

IQ4_XS (15.7 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_S at 10.0 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
Parameters35.5B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized bybyteshape
FamilyQwen
Licenseapache-2.0
Downloads (HF)4,736
Last updated2026-05-20

Frequently asked questions about Qwen3.6 35B A3B

How much VRAM does Qwen3.6 35B A3B need?

About 16.9 GB at IQ4_XS with an 8K context window. That is the 15.7 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 Qwen3.6 35B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.6 35B A3B GGUF?

It depends on the quant: IQ2_S is 10.0 GB, IQ3_S is 13.6 GB, IQ4_XS is 15.7 GB, IQ4_XS is 17.6 GB, IQ4_XS is 18.6 GB.

What context length does Qwen3.6 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 2.8 GB at 32K.

Where can I download Qwen3.6 35B A3B GGUF?

The files are on Hugging Face in the byteshape/Qwen3.6-35B-A3B-MTP-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 Qwen3.6 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 Qwen3.6 35B A3B on 8 GB VRAM?

Yes, using the IQ2_S quantized model which is 10.02 GB and requires about 11.2 GB VRAM at 8 k context.

Does this model support text only or also vision?

It supports vision; llama.cpp will auto‑download the vision projector on first run.

What is MTP and how does it affect inference?

MTP allows the model to predict multiple tokens per forward pass, speeding decoding on GPUs for predictable workloads.

Other GGUFs of Qwen3.6-35B-A3B

Similar models

Browse all →

More from byteshape

All by byteshape →

More Qwen models

All Qwen →

Other large models

All large models →