QW

Qwen3 VL 30B A3B Thinking

QwenGGUF by bartowskiUpdated 2025-10-31
Download on Hugging Face
Parameters30.5B
Context256K
Layers48
Architectureqwen3vlmoe
Smallest quant0.1 GB
Quick answer

Qwen3 VL 30B A3B Thinking needs about 19.9 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.1 GB to 61.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3 VL 30B A3B Thinking – 30.5B parameter vision‑language model

Qwen3 VL 30B A3B Thinking is a 30.5B parameter model with 3B active mixture‑of‑experts parameters. It supports 262144 token context and is licensed under apache‑2.0. The model excels in multimodal reasoning and vision tasks.

Good at

  • Vision‑language reasoning
  • Long‑context text and video understanding
  • Spatial perception and grounding

Limits

  • No vision support in some quantizations
  • Large memory requirement for full precision
  • Requires 256K context for full capability

Best for

  • Multimodal chatbots
  • Video analysis pipelines
  • Spatial reasoning applications

Who it’s for. Developers building advanced vision‑language assistants or research teams needing deep multimodal understanding. The model is suitable for cloud deployments where large VRAM and RAM are available.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.4 GB
Fits Get file →
IQ2_XXS7.6 GB 8.9 GB
Too big Get file →
IQ2_XS8.7 GB 10.0 GB
Too big Get file →
IQ2_S8.7 GB 10.0 GB
Too big Get file →
IQ2_M9.9 GB 11.2 GB
Too big Get file →
Q2_K10.9 GB 12.2 GB
Too big Get file →
Q2_K_L11.2 GB 12.5 GB
Too big Get file →
IQ3_XXS12.2 GB 13.5 GB
Too big Get file →
IQ3_XS12.7 GB 14.0 GB
Too big Get file →
Q3_K_S13.4 GB 14.7 GB
Too big Get file →
IQ3_M14.1 GB 15.4 GB
Too big Get file →
Q3_K_M14.1 GB 15.4 GB
Too big Get file →
Q3_K_L14.6 GB 15.9 GB
Too big Get file →
Q3_K_XL14.9 GB 16.2 GB
Too big Get file →
IQ4_XS16.5 GB 17.8 GB
Too big Get file →
IQ4_NL17.4 GB 18.7 GB
Too big Get file →
Q4_017.6 GB 18.9 GB
Too big Get file →
Q4_K_S18.0 GB 19.3 GB
Too big Get file →
Q4_K_M18.6 GB 19.9 GB
Too big Get file →
Q4_K_L18.9 GB 20.2 GB
Too big Get file →
Q4_119.2 GB 20.5 GB
Too big Get file →
Q5_K_S21.1 GB 22.4 GB
Too big Get file →
Q5_K_M21.7 GB 23.0 GB
Too big Get file →
Q5_K_L21.9 GB 23.2 GB
Too big Get file →
Q6_K25.1 GB 26.4 GB
Too big Get file →
Q6_K_L25.3 GB 26.6 GB
Too big Get file →
Q8_032.5 GB 33.8 GB
Too big Get file →
BF1661.1 GB (2 parts) 62.4 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (7.57 GB, 8.9 GB memory) or IQ2_XS (8.66 GB, 10 GB memory). For 16 GB VRAM, Q4_K_M (18.63 GB, 19.9 GB memory) or Q4_K_L (18.86 GB, 20.2 GB memory) are suitable. For 32 GB VRAM, Q8_0 (32.48 GB, 33.8 GB memory) provides full precision.

What GPU do you need for Qwen3 VL 30B A3B Thinking?

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: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_M (9.9 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_L (14.6 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_L (21.9 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (25.3 GB file, about 26.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (32.5 GB file, about 33.8 GB in use).

Which Qwen3 VL 30B A3B Thinking quant should you choose?

Q4_K_M is the usual starting point for Qwen3 VL 30B A3B Thinking: it balances file size and quality well. Here it is a 18.6 GB file.

The Q8_0 file is 32.5 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 the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vlmoe
Parameters30.5B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bybartowski
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,889
Last updated2025-10-31

Frequently asked questions about Qwen3 VL 30B A3B Thinking

How much VRAM does Qwen3 VL 30B A3B Thinking need?

About 19.9 GB at Q4_K_M with an 8K context window. That is the 18.6 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 VL 30B A3B Thinking on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.1 GB, IQ2_XXS is 7.6 GB, IQ2_XS is 8.7 GB, IQ2_S is 8.7 GB, IQ2_M is 9.9 GB, Q2_K is 10.9 GB and 22 more.

What context length does Qwen3 VL 30B A3B Thinking support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Qwen3 VL 30B A3B Thinking GGUF?

The files are on Hugging Face in the bartowski/Qwen_Qwen3-VL-30B-A3B-Thinking-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 VL 30B A3B Thinking 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 VL 30B A3B Thinking on 8 GB VRAM?

Use the IQ2_XXS or IQ2_XS quantizations; they require 8.9 or 10 GB memory at 8k context, which is close to 8 GB VRAM but may need swap.

Does the model support vision tasks?

Yes, it has detected abilities for reasoning and vision, with advanced spatial perception and video understanding.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Qwen3-VL-30B-A3B-Thinking

Similar models

Browse all →

More from bartowski

All by bartowski →

More Qwen models

All Qwen →

Other medium models

All medium models →