Loading…
Loading…
Models / Qwen3-Coder
4 models (30B to 480B) · ↓ 3.4M downloads a month · from $0.18/h on 2x RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen3-Coder-30B-A3B-Instruct | vLLM | 61 GB | 71 GB | $0.89/h 2x Nvidia A40 |
| AWQ 4bit (cyankiwi)cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit | vLLM | 18 GB | 23.2 GB | $0.24/h RTX 3090 |
| AWQ (QuantTrio)QuantTrio/Qwen3-Coder-30B-A3B-Instruct-AWQ | vLLM | 17 GB | 21.8 GB | $0.18/h 2x RTX 3060 |
| GPTQ Int8 (QuantTrio)QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 | vLLM | 32 GB | 38.7 GB | $0.45/h Nvidia A40 |
| AWQ (stelterlab)stelterlab/Qwen3-Coder-30B-A3B-Instruct-AWQ | vLLM | 17 GB | 21.7 GB | $0.18/h 2x RTX 3060 |
| FP4 (NVFP4)NVFP4/Qwen3-Coder-30B-A3B-Instruct-FP4 | vLLM | 18 GB | 23.2 GB | $0.24/h RTX 3090 |
| AWQ (dark-side-of-the-code)dark-side-of-the-code/Qwen3-Coder-30B-A3B-Instruct-AWQ | vLLM | 17 GB | 21.7 GB | $0.18/h 2x RTX 3060 |
| AWQ (AIDXteam)AIDXteam/Qwen3-Coder-30B-A3B-Instruct-AWQ | vLLM | 17 GB | 21.7 GB | $0.18/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen3-Coder-30B-A3B-Instruct-FP8 | vLLM | 31 GB | 37.8 GB | $0.45/h Nvidia A40 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | vLLM | 482 GB | 540.3 GB | $11.77/h 8x RTX PRO 6000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen3-Coder-480B-A35B-Instruct | vLLM | 960 GB | 1071.5 GB | $44.03/h 8x Nvidia H200 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").