gpt-neox-20b
by EleutherAI
20.7B params · text-generation · 584 likes · 657.8k downloads
gpt-neox-20b is a 20.7B parameter model. At Q4 quantization it requires 10GB of VRAM. It runs comfortably on GeForce RTX 4090 (63 tok/s), GeForce RTX 5090 (94 tok/s), A100 PCIe 80 GB (115 tok/s).
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 63 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 94 tok/s | comfortable |
| M4 Max 128GB | 128GB | 23 tok/s | tight |
| M4 Pro 48GB | 48GB | 11 tok/s | tight |
| M4 Pro 24GB | 24GB | 11 tok/s | tight |
| A100 PCIe 80 GB | 80GB | 115 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 233 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 55 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 46 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 44 tok/s | comfortable |