QW

Qwen3.6 35B A3B 2Bit GSQ RCO

QwenGGUF by chtisgitUpdated 2026-10-22
Download on Hugging Face
Parameters31.6B
Context256K
Layers40
Architectureqwen35moe
Smallest quant11.6 GB
Quick answer

Qwen3.6 35B A3B 2Bit GSQ RCO needs about 12.8 GB of memory at its main file (a 11.6 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 RCO – 2‑bit quantized MoE LLM

Qwen3.6 35B A3B 2Bit GSQ RCO is a 31.6B‑parameter model with 3B active experts. It uses 2‑bit GSQ for routed‑expert MLPs and INT8 for attention, shared experts, and LM head. The GGUF file is 11.59 GB and requires about 12.8 GB VRAM at 8 k context.

Good at

  • Reasoning
  • Tools usage
  • Vision tasks

Limits

  • No vision support on older CUDA builds
  • Worse coding performance than GSQ GGUF
  • Requires recent llama.cpp (b11390+)

Best for

  • Chatting with long context
  • Reasoning queries
  • Tool‑augmented tasks

Who it’s for. Developers and researchers needing a memory‑efficient Qwen3.6 variant for long‑context chat and reasoning. It is suitable for GPU setups with at least 12 GB VRAM and recent CUDA drivers.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—11.6 GB 12.8 GB
Too big Get file →

For 12 GB VRAM, use the 11.59 GB GGUF file. The estimated memory usage is 12.8 GB at 8 k context. No other quants are listed, so this is the recommended choice.

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

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 (11.6 GB file, about 12.8 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters31.6B (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)2,435
Last updated2026-10-22

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

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

About 12.8 GB at its main file with an 8K context window. That is the 11.6 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 RCO on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: file is 11.6 GB.

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

The files are on Hugging Face in the chtisgit/Qwen3.6-35B-A3B-2Bit-GSQ-RCO-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 RCO 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 model requires about 12.8 GB VRAM at 8 k context, so 8 GB is insufficient.

Does it support vision?

The model has detected vision ability, but the GGUF release lacks vision support on older CUDA builds.

Is it better for coding than the GSQ GGUF?

No, it performs worse at coding, especially web code; use the GSQ GGUF instead.

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 medium models

All medium models →