QW

qwen36 35b a3b distill

QwenGGUF by freakyskittleUpdated 2026-10-29
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant3.7 GB
Quick answer

qwen36 35b a3b distill needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 3.7 GB (F16) to 37.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Qwen3.6 35B A3B Distill – a 35.5B parameter, mixture‑of‑experts model

This model is a 35.5B parameter Qwen variant with a 262144 token context window. It is released under the apache-2.0 license and is available in multiple GGUF quantizations. The model supports reasoning and tool usage.

Good at

  • Large context reasoning
  • Tool integration
  • High‑capacity text generation

Limits

  • Requires 262144 token context
  • No vision support
  • Apache‑2.0 license restricts commercial use

Best for

  • Research on long‑form reasoning
  • Tool‑driven applications
  • Controlled testing environments

Who it’s for. Researchers and developers needing a large‑context LLM for text‑only tasks. The model is best suited for experimental or controlled use due to its reduced safety filtering.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F163.7 GB 4.9 GB
Fits Get file →
TQ1_08.1 GB 9.3 GB
Too big Get file →
TQ2_09.7 GB 10.9 GB
Too big Get file →
IQ4_XS19.4 GB 20.6 GB
Too big Get file →
Q4_K_S20.4 GB 21.6 GB
Too big Get file →
Q4_K_M21.7 GB 22.9 GB
Too big Get file →
Q6_K29.2 GB 30.4 GB
Too big Get file →
Q8_037.8 GB 39.0 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K_S quant (21.6 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (22.9 GB) or Q6_K (30.4 GB) are suitable. For 32 GB VRAM, Q8_0 (39 GB) or Q6_K provide the best performance.

What GPU do you need for qwen36 35b a3b distill?

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: the best quant that fits is F16 (3.7 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (3.7 GB file, about 4.9 GB in use).
  • 12 GB VRAM: the best quant that fits is TQ2_0 (9.7 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is TQ2_0 (9.7 GB file, about 10.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.7 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).

Which qwen36 35b a3b distill quant should you choose?

Q4_K_M is the usual starting point for qwen36 35b a3b distill: it balances file size and quality well. Here it is a 21.7 GB file.

The Q8_0 file is 37.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is F16 at 3.7 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized byfreakyskittle
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,773
Last updated2026-10-29

Frequently asked questions about qwen36 35b a3b distill

How much VRAM does qwen36 35b a3b distill need?

About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 qwen36 35b a3b distill on an 8 GB GPU?

Yes, with F16: the 3.7 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of qwen36 35b a3b distill GGUF?

It depends on the quant: F16 is 3.7 GB, TQ1_0 is 8.1 GB, TQ2_0 is 9.7 GB, IQ4_XS is 19.4 GB, Q4_K_S is 20.4 GB, Q4_K_M is 21.7 GB and 2 more.

What context length does qwen36 35b a3b distill 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 qwen36 35b a3b distill GGUF?

The files are on Hugging Face in the freakyskittle/qwen36-35b-a3b-distill repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does qwen36 35b a3b distill 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 Q4_K_S quant uses 21.6 GB memory at 8k context, which exceeds 8 GB VRAM. It is not feasible without swapping or off‑loading.

Does this model support vision tasks?

No, the model is text‑only; the vision tower has been stripped from the safetensors.

Is the model safe for production use?

The safety filtering is significantly reduced. Use only in research or controlled environments and monitor outputs.

Other GGUFs of Huihui-Qwen3.6-35B-A3B-abliterated

Similar models

Browse all →

More from freakyskittle

All by freakyskittle →

More Qwen models

All Qwen →

Other large models

All large models →