QW

Qwen3.8 35B A3B Distill

QwenGGUF by empero-aiUpdated 2026-09-16
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant12.6 GB
Quick answer

Qwen3.8 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 10 quants, from 12.6 GB (IQ2_M) to 71.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Qwen3.8-35B-A3B Distill: a 35B Mixture‑of‑Experts model with 3B active per token

Qwen3.8-35B-A3B Distill is a 35B parameter model that activates only 3B parameters per token. It supports a native 262,144‑token context and includes vision capabilities. The model is released under the Apache‑2.0 license.

Good at

  • Reasoning with chain‑of‑thought
  • Mathematics and code tasks
  • Sparse MoE efficiency

Limits

  • Requires recent llama.cpp with Qwen3.6 MoE support
  • Whole weight file must fit in RAM or VRAM
  • Vision behaviour not evaluated in distillation

Best for

  • Long‑form reasoning
  • Complex math and coding prompts
  • Deploying on a single GPU with limited VRAM

Who it’s for. Developers and researchers needing a large‑scale reasoning model that can run on a single GPU. The model is suitable for applications requiring long context and sparse MoE efficiency.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M12.6 GB 13.7 GB
Too big Get file →
Q2_K13.8 GB 15.0 GB
Too big Get file →
IQ3_M16.3 GB 17.5 GB
Too big Get file →
Q3_K_M17.7 GB 18.9 GB
Too big Get file →
IQ4_XS19.6 GB 20.8 GB
Too big Get file →
Q4_K_M21.7 GB 22.9 GB
Too big Get file →
Q5_K_M25.3 GB 26.5 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 →
BF1671.1 GB 72.3 GB
Too big Get file →

For 8 GB VRAM, use IQ2_M (12.56 GB) or Q2_K (13.84 GB). For 16 GB VRAM, Q3_K_M (17.66 GB) or Q4_K_M (21.71 GB) are suitable. Higher‑bit quants provide better quality but need more memory.

What GPU do you need for Qwen3.8 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: 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 Q2_K (13.8 GB file, about 15.0 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 Qwen3.8 35B A3B Distill quant should you choose?

Q4_K_M is the usual starting point for Qwen3.8 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 IQ2_M at 12.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized byempero-ai
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,229,816
Last updated2026-09-16

Frequently asked questions about Qwen3.8 35B A3B Distill

How much VRAM does Qwen3.8 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 Qwen3.8 35B A3B Distill on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.8 35B A3B Distill GGUF?

It depends on the quant: IQ2_M is 12.6 GB, Q2_K is 13.8 GB, IQ3_M is 16.3 GB, Q3_K_M is 17.7 GB, IQ4_XS is 19.6 GB, Q4_K_M is 21.7 GB and 4 more.

What context length does Qwen3.8 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 Qwen3.8 35B A3B Distill GGUF?

The files are on Hugging Face in the empero-ai/Qwen3.8-35B-A3B-Distill-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 Qwen3.8 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 Qwen3.8-35B-A3B Distill on 8 GB VRAM?

Use the IQ2_M or Q2_K quant, which are 12.56 GB and 13.84 GB respectively, and ensure the runtime supports Qwen3.6 MoE.

Does this model support vision tasks?

The vision tower is inherited from the base model, but vision behaviour was not evaluated in the distillation.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.8-35B-A3B-Distill

Similar models

Browse all →

More from empero-ai

All by empero-ai →

More Qwen models

All Qwen →

Other large models

All large models →