Configure a rig →

Qwen0.6B paramspopular

Qwen3 0.6B Base locally

Qwen3 0.6B Base is an open-weight LLM from the Qwen family with 0.6B parameters. Main use: chat, RAG and general assistance. Detected minimum hardware: GTX 1650 (4 GB).

Check on my GPU →Hugging Face ↗

Technical facts

Parameters0.6B

Q4_K_M0.4 GB

Q5_K_M0.5 GB

Q80.7 GB

FP161.3 GB

FamilyQwen

Last sync2026-05-12

Available quantizations

GGUF weights

Q4_K_M

0.4GB

Acceptable. Good compromise when VRAM is limited.

Q5_K_M

0.5GB

Good quality. Sweet spot for size and precision.

Q8

0.7GB

Near-FP16 quality. Comfortable for production.

FP16

1.3GB

Reference precision. Maximum quality, doubled VRAM.

Compatible GPUs

12 single-GPU

GPUs that can run Qwen3 0.6B Base on a single card, ranked by VRAM headroom.

1.3 / 4 GBcomfortable · FP16

1.3 / 6 GBcomfortable · FP16

1.3 / 6 GBcomfortable · FP16

1.3 / 6 GBcomfortable · FP16

1.3 / 6 GBcomfortable · FP16

1.3 / 6 GBcomfortable · FP16

1.3 / 6 GBcomfortable · FP16

6 GB · Arc Alchemist

1.3 / 6 GBcomfortable · FP16

1.3 / 8 GBcomfortable · FP16

1.3 / 8 GBcomfortable · FP16

1.3 / 8 GBcomfortable · FP16

1.3 / 8 GBcomfortable · FP16

Recommended multi-GPU rigs

2x / 4x consumer GPUs

For Qwen3 0.6B Base at higher quantization or with more context, a multi-GPU rig gives more headroom.

1.3 / 8 GBcomfortable · FP16

2× GTX 1060 6GB

12 GB · GTX 10

1.3 / 12 GBcomfortable · FP16

12 GB · GTX 16

1.3 / 12 GBcomfortable · FP16

2× GTX 1660 Super

12 GB · GTX 16

1.3 / 12 GBcomfortable · FP16

2× GTX 1660 Ti

12 GB · GTX 16

1.3 / 12 GBcomfortable · FP16

2× RTX 2060 6GB

12 GB · RTX 20

1.3 / 12 GBcomfortable · FP16

2× RTX 3050 6GB

12 GB · RTX 30

1.3 / 12 GBcomfortable · FP16

12 GB · Arc Alchemist

1.3 / 12 GBcomfortable · FP16

Recommended rig

2× GTX 1650

Qwen3 0.6B Base 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