GLM-5.2
by zai-org
753B params · text-generation · 1.8k likes · 27.4k downloads
GLM-5.2 is a 753B parameter model. At Q4 quantization it requires 377GB of VRAM. It requires a GPU with at least 377GB of VRAM.
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Novita | 47 tok/s | ||
| Together AI | 111 tok/s | ||
| Fireworks | 51 tok/s | ||
| Featherless | |||
| Z.ai | 38 tok/s | ||
| deepinfra | 31 tok/s |