Qwen3-0.6B
by Qwen
752M params · text-generation · 1.1k likes · 12.2M downloads
Qwen3-0.6B is a 752M parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (1746 tok/s), GeForce RTX 5090 (2619 tok/s), M4 Max 128GB (639 tok/s).
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 1746 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 2619 tok/s | comfortable |
| M4 Max 128GB | 128GB | 639 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 319 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 319 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 3200 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 6437 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 1544 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 1277 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 1239 tok/s | comfortable |