QW

Qwen3.6 35B A3b pruned v2

QwenGGUF by gatilinUpdated 2026-09-12
Download on Hugging Face
Parameters26.6B
Context256K
Layers40
Architectureqwen35moe
Smallest quant16.3 GB
Quick answer

Qwen3.6 35B A3b pruned v2 needs about 17.4 GB of memory at its main file (a 16.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.6 35B A3b pruned v2 – a pruned, long‑context, MoE model

Qwen3.6 35B A3b pruned v2 is a causal language model with a 262,144‑token native context. It is a mixture‑of‑experts architecture with 256 experts, 8 activated per token. The GGUF file is 16.27 GB and requires about 17.4 GB of VRAM at 8 k context.

Good at

  • Long‑context reasoning
  • MoE efficient inference
  • Open‑weight compatibility

Limits

  • No vision support
  • Requires 32 GB RAM for full 256 k context
  • Only available in GGUF format

Best for

  • Chatbots needing large context
  • Code generation with MoE efficiency
  • Local inference on macOS ARM64

Who it’s for. Developers and researchers who need a large‑context, open‑weight LLM that can run locally with llama.cpp. The model is suitable for applications that benefit from the mixture‑of‑experts architecture and long‑context handling.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—16.3 GB 17.4 GB
Too big Get file →

The provided GGUF file is 16.27 GB and needs about 17.4 GB of VRAM at 8 k context. For systems with 8 GB VRAM, a lower‑bit quantization such as Q3_K_M or Q4_K_S would be required, but these are not included in the current file list. For 16 GB VRAM, the current file can be used with a reduced context size.

What GPU do you need for Qwen3.6 35B A3b pruned v2?

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 the main file (16.3 GB file, about 17.4 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters26.6B (approximate, mixture of experts)
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bygatilin
FamilyQwen
Licenseapache-2.0
Downloads (HF)18,255
Last updated2026-09-12

Frequently asked questions about Qwen3.6 35B A3b pruned v2

How much VRAM does Qwen3.6 35B A3b pruned v2 need?

About 17.4 GB at its main file with an 8K context window. That is the 16.3 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 pruned v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.6 35B A3b pruned v2 GGUF?

It depends on the quant: file is 16.3 GB.

What context length does Qwen3.6 35B A3b pruned v2 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 pruned v2 GGUF?

The files are on Hugging Face in the gatilin/Qwen3.6-35B-A3b-pruned-v2 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 pruned v2 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 current GGUF file requires about 17.4 GB of VRAM at 8 k context, so it cannot run on 8 GB VRAM without further quantization.

Does this model support vision?

No, the GGUF file contains only language weights and does not include vision capabilities.

What platform is required to run this model?

The repository includes a macOS ARM64 / Metal build; other platforms can use llama.cpp to load the GGUF file.

Other GGUFs of Qwen3.6-35B-A3B

Similar models

Browse all →

More from gatilin

All by gatilin →

More Qwen models

All Qwen →

Other medium models

All medium models →