GLM-4-9B-0414
by zai-org
9.4B params · text-generation · 99 likes · 14.4k downloads
GLM-4-9B-0414 is a 9.4B parameter model. At Q4 quantization it requires 5GB of VRAM. It runs comfortably on GeForce RTX 4090 (139 tok/s), GeForce RTX 5090 (209 tok/s), M4 Max 128GB (51 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Featherless |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 139 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 209 tok/s | comfortable |
| M4 Max 128GB | 128GB | 51 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 25 tok/s | tight |
| M4 Pro 24GB | 24GB | 25 tok/s | tight |
| A100 PCIe 80 GB | 80GB | 255 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 514 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 123 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 102 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 99 tok/s | comfortable |