GLM-5
by zai-org
754B params · text-generation · 2.1k likes · 59.5k downloads
GLM-5 is a 754B 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 | 35 tok/s | ||
| Together AI | 107 tok/s | ||
| Featherless | |||
| Z.ai | 37 tok/s | ||
| deepinfra | 37 tok/s |