Our catalog tracks 5 GLM models (31.2B–753.9 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. 3 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 | GLM-4.7-Flash | 31.2B MoE 3B act. | 18.76 | RX 7900 XT 20GB ≈169.7 tok/s est. | RTX 5090 32GB ≈380.1 tok/s est. | Search Amazon (affiliate) |
| 2 | GLM-4.5-Air | 110.5B MoE 12B act. | 64.18 | Mac Studio M3 Ultra 96GB ≈43.4 tok/s est. | Mac Studio M3 Ultra 96GB ≈43.4 tok/s est. | Search Amazon (affiliate) |
| 3 | GLM-4.5 | 358.3B MoE 32B act. | 204.47 | No retail GPU fits | — | — |
| 4 | GLM-5.2 | 753.3B MoE 40B act. | 423.31 | No retail GPU fits | — | — |
| 5 | GLM-5.1 | 753.9B MoE 40B act. | 423.65 | No retail GPU fits | — | — |