Our catalog tracks 7 coding LLMs (7.6B–480.2 parameters). For each, the table shows the cheapest retail GPU that fully fits it at Q4 / 8K context and the fastest retail GPU, with decode tok/s. Fit means weights + KV cache + 1 GB runtime overhead within 95% of VRAM — not weights alone. 1 of them exceed every retail GPU we track and are marked accordingly. Methodology.
| # | Model | Params | Q4/8K needs (GB) | Best value GPU (fits) | Fastest retail GPU | Buy |
|---|---|---|---|---|---|---|
| 1 | Qwen2.5-Coder-7B-Instruct | 7.6B | 6.7 | Arc B570 10GB ≈31.8 tok/s est. | RTX 5090 32GB ≈150.0 tok/s est. | Search Amazon (affiliate) |
| 2 | Qwen2.5-Coder-14B-Instruct | 14.8B | 12.1 | RX 7600 XT 16GB ≈12.4 tok/s est. | RTX 5090 32GB ≈77.1 tok/s est. | Search Amazon (affiliate) |
| 3 | Devstral-Small-2507 | 23.6B | 18.7 | RX 7900 XT 20GB ≈21.6 tok/s est. | RTX 5090 32GB ≈48.3 tok/s est. | Search Amazon (affiliate) |
| 4 | Qwen3-Coder-30B-A3B-Instruct | 30.5B MoE 3B act. | 18.38 | RX 7900 XT 20GB ≈169.7 tok/s est. | RTX 5090 32GB ≈380.1 tok/s est. | Search Amazon (affiliate) |
| 5 | Qwen2.5-Coder-32B-Instruct | 32.8B | 25.6 | Mac mini M4 32GB ≈2.3 tok/s est. | RTX 5090 32GB ≈34.8 tok/s est. | Search Amazon (affiliate) |
| 6 | Qwen3-Coder-Next | 79.7B MoE 3B act. | 45.44 | Mac mini M4 Pro 64GB ≈57.9 tok/s est. | RTX 6000 Ada 48GB ≈203.6 tok/s est. | Search Amazon (affiliate) |
| 7 | Qwen3-Coder-480B-A35B-Instruct | 480.2B MoE 35B act. | 272.11 | No retail GPU fits | — | — |