Loading…
Loading…
Models / GLM-5.2
2 models (~753B to ~753B) · ↓ 933.8K downloads a month · from $11.77/h on 8x RTX PRO 6000 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 |
|---|---|---|---|---|
| Originalzai-org/GLM-5.2 | vLLM | 1507 GB | 1711.2 GB | $132.05/h 8x Nvidia B300 |
| NVFP4 (nvidia)nvidia/GLM-5.2-NVFP4 | vLLM | 465 GB | 553.6 GB | $11.77/h 8x RTX PRO 6000 |
| colibri int4 g64 with int8 mtp (mastouri)mastouri/GLM-5.2-colibri-int4-g64-with-int8-mtp | vLLM | 429 GB | 514.1 GB | $11.77/h 8x RTX PRO 6000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalzai-org/GLM-5.2-FP8 | vLLM | 756 GB | 876.7 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").