Configure a rig →

Qwen8B params128k contextpopular

Qwen 3 8B locally

Qwen 3 8B is an open-weight LLM from the Qwen family with 8B parameters. Main use: chat, RAG and general assistance. Detected minimum hardware: GTX 1060 6GB (6 GB).

Check on my GPU →Hugging Face ↗

Technical facts

Parameters8B

Max context128k

Q4_K_M5.0 GB

Q5_K_M6.1 GB

Q88.9 GB

FP1617.9 GB

FamilyQwen

Last sync2026-05-12

Available quantizations

GGUF weights

Q4_K_M

5.0GB

Acceptable. Good compromise when VRAM is limited.

Q5_K_M

6.1GB

Good quality. Sweet spot for size and precision.

Q8

8.9GB

Near-FP16 quality. Comfortable for production.

FP16

17.9GB

Reference precision. Maximum quality, doubled VRAM.

Compatible GPUs

12 single-GPU

GPUs that can run Qwen 3 8B on a single card, ranked by VRAM headroom.

5.0 / 6 GBcomfortable · Q4

5.0 / 6 GBcomfortable · Q4

5.0 / 6 GBcomfortable · Q4

5.0 / 6 GBcomfortable · Q4

5.0 / 6 GBcomfortable · Q4

5.0 / 6 GBcomfortable · Q4

6 GB · Arc Alchemist

5.0 / 6 GBcomfortable · Q4

6.1 / 8 GBcomfortable · Q5

6.1 / 8 GBcomfortable · Q5

6.1 / 8 GBcomfortable · Q5

6.1 / 8 GBcomfortable · Q5

6.1 / 8 GBcomfortable · Q5

Recommended multi-GPU rigs

2x / 4x consumer GPUs

For Qwen 3 8B at higher quantization or with more context, a multi-GPU rig gives more headroom.

6.1 / 8 GBcomfortable · Q5

2× GTX 1060 6GB

12 GB · GTX 10

8.9 / 12 GBcomfortable · Q8

12 GB · GTX 16

8.9 / 12 GBcomfortable · Q8

2× GTX 1660 Super

12 GB · GTX 16

8.9 / 12 GBcomfortable · Q8

2× GTX 1660 Ti

12 GB · GTX 16

8.9 / 12 GBcomfortable · Q8

2× RTX 2060 6GB

12 GB · RTX 20

8.9 / 12 GBcomfortable · Q8

2× RTX 3050 6GB

12 GB · RTX 30

8.9 / 12 GBcomfortable · Q8

12 GB · Arc Alchemist

8.9 / 12 GBcomfortable · Q8

Recommended rig

2× GTX 1650

Qwen 3 8B with Ubuntu, vLLM, Open WebUI and the model already downloaded.

Similar models

VRAM estimates: parameters x bits/8 plus margin. Real performance varies by engine, context length and batch size.
sync: 2026-05-12