QW

Qwen3 Coder 30B A3B Instruct SOTA

QwenGGUF by CISCaiUpdated 2025-08-01
Download on Hugging Face
Parameters30.5B
Context—
Layers—
Architecture—
Smallest quant0.1 GB
Quick answer

Qwen3 Coder 30B A3B Instruct SOTA needs about 12.2 GB of memory at IQ2_M (a 10.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 13 quants, from 0.1 GB to 61.1 GB (BF16).

Qwen3 Coder 30B A3B Instruct – large‑scale coding model

Qwen3-Coder-30B-A3B-Instruct is a 30.5 B parameter causal language model. It supports 262,144 native tokens and can be extended to 1 M tokens with Yarn. The model is optimized for agentic coding and tool‑calling tasks.

Good at

  • Agentic coding and tool calling
  • Long‑context repository understanding
  • High performance on coding benchmarks

Limits

  • No vision support
  • Requires recent llama.cpp (≥April 2025)
  • Large memory for full precision

Best for

  • Code generation in IDEs
  • Automated code review tools
  • Large‑scale code search

Who it’s for. Developers and researchers needing a powerful coding assistant. The model is suitable for local deployment on systems with sufficient VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 0.6 GB
Fits Get file →
IQ1_S6.8 GB 8.1 GB
Too big Get file →
IQ1_M7.5 GB 8.9 GB
Too big Get file →
IQ2_XXS8.5 GB 10.0 GB
Too big Get file →
IQ2_XS9.4 GB 11.1 GB
Too big Get file →
IQ2_S9.6 GB 11.3 GB
Too big Get file →
IQ2_M10.5 GB 12.2 GB
Too big Get file →
IQ3_XXS12.2 GB 14.1 GB
Too big Get file →
IQ3_XS12.9 GB 14.9 GB
Too big Get file →
IQ3_S13.6 GB 15.7 GB
Too big Get file →
IQ3_M13.8 GB 15.9 GB
Too big Get file →
IQ4_XS16.6 GB 19.1 GB
Too big Get file →
BF1661.1 GB (3 parts) 68.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.81 GB file, ~8.1 GB VRAM). For 12 GB VRAM, IQ2_S (9.6 GB file, ~11.3 GB VRAM). For 20 GB VRAM, IQ4_XS (16.61 GB file, ~19.1 GB VRAM). BF16 requires 61.1 GB file and ~69 GB VRAM.

What GPU do you need for Qwen3 Coder 30B A3B Instruct SOTA?

These figures add the file size, an fp16 KV cache at an 8K context window 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 0.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_S (9.6 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (13.8 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (16.6 GB file, about 19.1 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ4_XS (16.6 GB file, about 19.1 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ4_XS (16.6 GB file, about 19.1 GB in use).

Which Qwen3 Coder 30B A3B Instruct SOTA quant should you choose?

IQ2_M (10.5 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.

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

Parameters30.5B

Source

Quantized byCISCai
FamilyQwen
Licenseapache-2.0
Downloads (HF)2,408
Last updated2025-08-01

Frequently asked questions about Qwen3 Coder 30B A3B Instruct SOTA

How much VRAM does Qwen3 Coder 30B A3B Instruct SOTA need?

About 12.2 GB at IQ2_M with an 8K context window. That is the 10.5 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 Coder 30B A3B Instruct SOTA on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3 Coder 30B A3B Instruct SOTA GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 6.8 GB, IQ1_M is 7.5 GB, IQ2_XXS is 8.5 GB, IQ2_XS is 9.4 GB, IQ2_S is 9.6 GB and 7 more.

Where can I download Qwen3 Coder 30B A3B Instruct SOTA GGUF?

The files are on Hugging Face in the CISCai/Qwen3-Coder-30B-A3B-Instruct-SOTA-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 Coder 30B A3B Instruct SOTA 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 Coder 30B on 8 GB VRAM?

Yes, using the IQ1_S quantization which uses about 8.1 GB VRAM at 8k context.

Does the model support image input?

No, this model has no vision capabilities.

What context length does it support natively?

It supports 262,144 tokens natively and can be extended to 1M tokens with Yarn.

Other GGUFs of Qwen3-Coder-30B-A3B-Instruct

Similar models

Browse all →

More from CISCai

All by CISCai →

More Qwen models

All Qwen →

Other medium models

All medium models →