Skip to content
localmodel.run

Text model · Qwen3

Qwen3 8B requirements

Qwen3 family · 8B params · released Apr 2025 · 23M Ollama pulls. Minimum to run at Q4_K_M: Nvidia GeForce RTX 3060 (12GB).

LicenseApache-2.0· Commercial OK↓ 8.6M/mo♥ 1.1Kon HuggingFace
Q4_K_M
5.03 GB
Q8_0
8.71 GB
Total @ Q4 (4k)
~6.5 GB
Context
32 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K3.4 GB est
Q3_K_M3.9 GB est
Q4_K_M (default)5.03 GB
Q5_K_M5.7 GB est
Q6_K6.6 GB est
Q8_08.71 GB
FP1616 GB

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run qwen3:8b
llama.cpp
$ llama-cli -hf Qwen/Qwen3-8B-GGUF:Q4_K_M
LM Studio
$ lms get Qwen/Qwen3-8B-GGUF

Which devices can run Qwen3 8B?

FAQ

How much VRAM or RAM does Qwen3 8B need?

At Q4_K_M, Qwen3 8B needs about 6.5 GB (weights ~5.03 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~10.2 GB.

Can Qwen3 8B run on a laptop?

Yes, Qwen3 8B fits on a 16 GB machine at Q4_K_M and runs on Apple Silicon or a 12 GB+ GPU comfortably.

Can I use Qwen3 8B commercially?

Yes. Qwen3 8B is licensed Apache-2.0, which permits commercial use.

Official Qwen/Qwen3-8B-GGUF HF repo lists Q4_K_M=5.03GB, Q8_0=8.71GB. Ollama library shows 5.2GB (rounded). Qwen3 released 2025-04-29. Context 32K native, extendable to 128K via YaRN.

Sources

Memory figures are estimates. See methodology.