Qwen / text-generation updated 1 year ago

Qwen3-30B-A3B-GGUF

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:

Params
Context
Downloads 30d
265 K
Likes
79
Commercial use: allowed apache-2.0 Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 38 days
▲ 121 K in the last 30 days (31.4%)
404 K241 K
Aug 15Aug 27Sep 9Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
Qwen3-30B-A3B-Q4_K_M.gguf Q4_K_M 18.6 GB 20.9 GB ⚠️ Tight — reduce context
Qwen3-30B-A3B-Q5_0.gguf Q5_0 21.1 GB 23.7 GB ⚠️ Tight — reduce context
Qwen3-30B-A3B-Q5_K_M.gguf Q5_K_M 21.7 GB 24.4 GB ❌ Won’t fit
Qwen3-30B-A3B-Q6_K.gguf Q6_K 25.1 GB 28.1 GB ❌ Won’t fit
Qwen3-30B-A3B-Q8_0.gguf Q8_0 32.5 GB 36.2 GB ❌ Won’t fit
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · Q4_K_M
$ ollama run qwen3-30b-a3b-gguf-qwen

# pin the quantization explicitly
$ ollama run qwen3-30b-a3b-gguf-qwen-q4_k_m
est. VRAM 20.9 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
apache-2.0
First seen on the Hub
2025-05-05
Base model
Qwen3-30B-A3B
Training datasets
undisclosed
Added to our catalog
2026-08-15

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-generation model