QW

Qwen3.6 35B A3B 2Bit GSQ hybrid

QwenGGUF by chtisgitUpdated 2026-10-22
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant12.2 GB
Quick answer

Qwen3.6 35B A3B 2Bit GSQ hybrid needs about 13.4 GB of memory at its main file (a 12.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.6 35B A3B 2Bit GSQ hybrid – low‑bit quantized MoE model

This GGUF model is a 2‑bit GSQ quantization of Qwen3.6‑35B‑A3B. It retains 34.7 B total parameters with 3 B active experts. The model supports vision and long‑context up to 262,144 tokens.

Good at

  • Long‑context reasoning
  • Vision tasks
  • Low‑bit inference

Limits

  • Requires recent llama.cpp (b11390 or newer)
  • Large VRAM for 8 k context (~13.4 GB)
  • No GPU‑specific optimizations beyond standard GGUF

Best for

  • Chatting with extended context
  • Image‑based question answering
  • Fine‑tuning on small datasets

Who it’s for. Engineers and researchers needing a compact MoE model with vision support. Suitable for deployment on GPUs with at least 13 GB VRAM and recent llama.cpp builds.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—12.2 GB 13.4 GB
Too big Get file →

For 8 k context, the single GGUF file is 12.22 GB and needs about 13.4 GB VRAM. If VRAM is limited, consider using a higher‑bit quant like Q8_0, but that is not available in this file list. The provided file is the only quant available.

What GPU do you need for Qwen3.6 35B A3B 2Bit GSQ hybrid?

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 the main file (12.2 GB file, about 13.4 GB in use).

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 bychtisgit
FamilyQwen
Licenseapache-2.0
Downloads (HF)9,384
Last updated2026-10-22

Frequently asked questions about Qwen3.6 35B A3B 2Bit GSQ hybrid

How much VRAM does Qwen3.6 35B A3B 2Bit GSQ hybrid need?

About 13.4 GB at its main file with an 8K context window. That is the 12.2 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 2Bit GSQ hybrid on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.6 35B A3B 2Bit GSQ hybrid GGUF?

It depends on the quant: file is 12.2 GB.

What context length does Qwen3.6 35B A3B 2Bit GSQ hybrid 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 2Bit GSQ hybrid GGUF?

The files are on Hugging Face in the chtisgit/Qwen3.6-35B-A3B-2Bit-GSQ-hybrid-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 2Bit GSQ hybrid 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 an RTX 3060 with 12 GB VRAM?

The model requires approximately 13.4 GB VRAM at 8 k context, so an RTX 3060 with 12 GB is insufficient for full context. Smaller context may reduce memory usage.

Does this model support vision tasks?

Yes, the GGUF includes a separate BF16/F32 vision‑projector GGUF for vision support.

What llama.cpp version is needed?

Use llama.cpp b11390 (4 Oct 2026) or newer; older builds crash on certain prompt lengths.

Other GGUFs of Qwen3.6-35B-A3B-2Bit-GSQ

Similar models

Browse all →

More from chtisgit

All by chtisgit →

More Qwen models

All Qwen →

Other large models

All large models →