Qwen2.5 7B hardware requirements
7.62B parameters. Needs about 5.7 GB at Q4_K_M with 8K context. Model card.
Memory needed at each quantization
| Quant | Quality | 8K context | 32K context |
|---|---|---|---|
| FP16 | Full quality | 16.3 GB | 17.7 GB |
| Q8_0 | Near-lossless | 9.2 GB | 10.6 GB |
| Q6_K | Excellent | 7.3 GB | 8.7 GB |
| Q5_K_M | Very good | 6.5 GB | 7.9 GB |
| Q4_K_M | Good, most popular | 5.7 GB | 7.1 GB |
| Q3_K_M | Noticeably degraded | 4.8 GB | 6.2 GB |
| Q2_K | Heavily degraded | 3.9 GB | 5.3 GB |
Run it with Ollama: ollama run qwen2.5:7b (downloads Q4_K_M by default).
Run it in the cloud
Don't want to buy hardware? Run Qwen2.5 7B on a rented GPU today.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.
Every GPU and Mac checked
| GPU | Runs? | Best fit |
|---|---|---|
| NVIDIA RTX 3060 12GB | Yes | Q8_0 · ~9.2 GB · ~27 tok/s |
| NVIDIA RTX 3070 | Yes | Q6_K · ~7.3 GB · ~43 tok/s |
| NVIDIA RTX 3080 10GB | Yes | Q8_0 · ~9.2 GB · ~56 tok/s |
| NVIDIA RTX 3090 | Yes | FP16 · ~16.3 GB · ~37 tok/s |
| NVIDIA RTX 4060 | Yes | Q6_K · ~7.3 GB · ~26 tok/s |
| NVIDIA RTX 4060 Ti 16GB | Yes | Q8_0 · ~9.2 GB · ~21 tok/s |
| NVIDIA RTX 5060 Ti 16GB | Yes | Q8_0 · ~9.2 GB · ~33 tok/s |
| NVIDIA RTX 4070 | Yes | Q8_0 · ~9.2 GB · ~37 tok/s |
| NVIDIA RTX 4070 Ti Super | Yes | Q8_0 · ~9.2 GB · ~50 tok/s |
| NVIDIA RTX 4080 | Yes | Q8_0 · ~9.2 GB · ~53 tok/s |
| NVIDIA RTX 4090 | Yes | FP16 · ~16.3 GB · ~40 tok/s |
| NVIDIA RTX 5070 | Yes | Q8_0 · ~9.2 GB · ~50 tok/s |
| NVIDIA RTX 5070 Ti | Yes | Q8_0 · ~9.2 GB · ~66 tok/s |
| NVIDIA RTX 5080 | Yes | Q8_0 · ~9.2 GB · ~71 tok/s |
| NVIDIA RTX 5090 | Yes | FP16 · ~16.3 GB · ~71 tok/s |
| AMD Radeon RX 7800 XT | Yes | Q8_0 · ~9.2 GB · ~46 tok/s |
| AMD Radeon RX 7900 XTX | Yes | FP16 · ~16.3 GB · ~38 tok/s |
| Apple M4 (16GB) | Yes | Q8_0 · ~9.2 GB · ~9 tok/s |
| Apple M1 (16GB) | Yes | Q8_0 · ~9.2 GB · ~5 tok/s |
| Apple M2 Pro (32GB) | Yes | FP16 · ~16.3 GB · ~8 tok/s |
| Apple M3 Max (64GB) | Yes | FP16 · ~16.3 GB · ~16 tok/s |
| Apple M4 Pro (48GB) | Yes | FP16 · ~16.3 GB · ~11 tok/s |
| Apple M4 Max (128GB) | Yes | FP16 · ~16.3 GB · ~21 tok/s |
| Apple M2 Ultra (192GB) | Yes | FP16 · ~16.3 GB · ~31 tok/s |