GLM-5.1-FP8
by zai-org
754B params · text-generation · 117 likes · 1.3M downloads
GLM-5.1-FP8 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 |
|---|---|---|---|
| Fireworks | 49 tok/s | ||
| Z.ai | 34 tok/s |