Qwen / text-generation updated 1 year ago

Qwen3-8B-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
236 K
Likes
240
Commercial use: allowed apache-2.0 Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 10 days
236 K184 K
Jul 28Jul 31Aug 3Aug 6

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
Qwen3-8B-Q4_K_M.gguf Q4_K_M 5.0 GB 6.0 GB ✅ Runs comfortably
Qwen3-8B-Q5_0.gguf Q5_0 5.7 GB 6.8 GB ✅ Runs comfortably
Qwen3-8B-Q5_K_M.gguf Q5_K_M 5.9 GB 6.9 GB ✅ Runs comfortably
Qwen3-8B-Q6_K.gguf Q6_K 6.7 GB 7.9 GB ✅ Runs comfortably
Qwen3-8B-Q8_0.gguf Q8_0 8.7 GB 10.1 GB ✅ Runs comfortably
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 qwen3-8b-gguf-qwen

# pin the quantization explicitly
$ ollama run qwen3-8b-gguf-qwen-q4_k_m
est. VRAM 6.0 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
apache-2.0
First seen on the Hub
2025-05-03
Base model
Qwen3-8B
Training datasets
undisclosed
Added to our catalog
2026-07-28

Family

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

Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.