Qwen2.5-Coder-3B-Instruct
by Qwen
3.1B params · text-generation · 96 likes · 125.4k downloads
Qwen2.5-Coder-3B-Instruct is a 3.1B parameter model. At Q4 quantization it requires 2GB of VRAM. It runs comfortably on GeForce RTX 4090 (425 tok/s), GeForce RTX 5090 (638 tok/s), M4 Max 128GB (155 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Nscale | 77 tok/s |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 425 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 638 tok/s | comfortable |
| M4 Max 128GB | 128GB | 155 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 77 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 77 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 779 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 1567 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 376 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 311 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 301 tok/s | comfortable |