QW

Qwen Qwen3 30B A3B

QwenGGUF by tensorblockUpdated 2026-01-27
Download on Hugging Face
Parameters30.5B
Context40K
Layers48
Architectureqwen3moe
Smallest quant11.3 GB
Quick answer

Qwen Qwen3 30B A3B needs about 12.6 GB of memory at Q2_K (a 11.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 11.3 GB (Q2_K) to 14.7 GB (Q3_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen Qwen3 30B A3B – 30.5B parameter MoE model

Qwen Qwen3 30B A3B is a causal language model with 30.5B total parameters and 3.3B active experts. It supports 32,768 token context natively and 131,072 with YaRN. The model is licensed under apache-2.0.

Good at

  • Reasoning
  • Tool use
  • Agent integration

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Mixture of experts limits activated experts

Best for

  • Complex logical reasoning
  • Agent-based tasks
  • Multilingual instruction following

Who it’s for. Developers needing a large MoE model for reasoning and agent tasks. Suitable for applications that can handle the model’s memory requirements and license terms.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.3 GB 12.6 GB
Too big Get file →
Q3_K_M14.7 GB 16.0 GB
Too big Get file →

For 8GB VRAM, the Q2_K quant file (11.26 GB) is recommended, estimating 12.6 GB memory at 8k context. If more memory is available, the Q3_K_M quant (14.71 GB) uses about 16 GB at 8k context. Both are approximate estimates.

What GPU do you need for Qwen Qwen3 30B A3B?

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 Q3_K_M (14.7 GB file, about 16.0 GB in use).

Which Qwen Qwen3 30B A3B quant should you choose?

Q2_K (11.3 GB) is the middle option in this repository. 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

Architectureqwen3moe
Parameters30.5B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context40,960 tokens
KV cache (fp16)96 KB per token

Source

Quantized bytensorblock
FamilyQwen
Licenseapache-2.0
Downloads (HF)962
Last updated2026-01-27

Frequently asked questions about Qwen Qwen3 30B A3B

How much VRAM does Qwen Qwen3 30B A3B need?

About 12.6 GB at Q2_K with an 8K context window. That is the 11.3 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 Qwen Qwen3 30B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen Qwen3 30B A3B GGUF?

It depends on the quant: Q2_K is 11.3 GB, Q3_K_M is 14.7 GB.

What context length does Qwen Qwen3 30B A3B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Qwen Qwen3 30B A3B GGUF?

The files are on Hugging Face in the tensorblock/Qwen_Qwen3-30B-A3B-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 Qwen Qwen3 30B A3B 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 30B A3B on 8GB VRAM?

The Q2_K quant file is 11.26 GB, which may fit with 8GB VRAM if memory is shared, but it is close to the limit. The Q3_K_M quant is larger at 14.71 GB and would exceed 8GB VRAM.

Does the model support vision tasks?

No, the model does not support vision.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Qwen3-30B-A3B

Similar models

Browse all →

More from tensorblock

All by tensorblock →

More Qwen models

All Qwen →

Other medium models

All medium models →