QW

Qwen3.6 35B A3B

QwenGGUF by noctrexUpdated 2026-04-16
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant20.3 GB
Quick answer

Qwen3.6 35B A3B needs about 23.2 GB of memory at MXFP4_MOE (a 22.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 20.3 GB (MXFP4_MOE) to 22.1 GB (MXFP4_MOE). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.6 35B A3B – a large vision‑enabled language model

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 released under the apache-2.0 license.

Good at

  • Vision‑enabled text generation
  • Agentic coding workflows
  • Large context handling

Limits

  • No vision support on older GPUs
  • Requires 8,000 token context for memory estimates
  • Mixture of Experts limits active parameters to 3B

Best for

  • Developing code assistants
  • Processing long documents
  • Building multimodal applications

Who it’s for. Engineers and researchers who need a stable, open‑weight model with vision capabilities and large context support. The model is suitable for developers building AI tools that require both text and image understanding.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE20.3 GB 21.4 GB
Too big Get file →
MXFP4_MOE22.1 GB 23.2 GB
Too big Get file →
MXFP4_MOE22.1 GB 23.2 GB
Too big Get file →

For 8 GB VRAM, choose the MXFP4_MOE quant with file size 20.27 GB; it estimates 21.4 GB memory at 8 k context. For 12 GB VRAM, the 22.06 GB variant uses about 23.2 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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is MXFP4_MOE (22.1 GB file, about 23.2 GB in use).

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

MXFP4_MOE (22.1 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is MXFP4_MOE at 20.3 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

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 bynoctrex
FamilyQwen
Licenseapache-2.0
Downloads (HF)926
Last updated2026-04-16

Frequently asked questions about Qwen3.6 35B A3B

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

About 23.2 GB at MXFP4_MOE with an 8K context window. That is the 22.1 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 Qwen3.6 35B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.4 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: MXFP4_MOE is 20.3 GB, MXFP4_MOE is 22.1 GB, MXFP4_MOE is 22.1 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 2.7 GB at 32K.

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

The files are on Hugging Face in the noctrex/Qwen3.6-35B-A3B-MXFP4_MOE-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 this model on 8 GB VRAM?

The 20.27 GB MXFP4_MOE quant estimates 21.4 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does the model support vision tasks?

Yes, it includes a vision encoder and can process images.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Qwen3.6-35B-A3B

Similar models

Browse all →

More from noctrex

All by noctrex →

More Qwen models

All Qwen →

Other large models

All large models →