II-Medical-8B-1706
by Intelligent-Internet
8.2B params · text-generation · 138 likes · 321 downloads
II-Medical-8B-1706 is a 8.2B parameter model. At Q4 quantization it requires 4GB of VRAM. It runs comfortably on GeForce RTX 4090 (160 tok/s), GeForce RTX 5090 (240 tok/s), M4 Max 128GB (58 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Featherless |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 160 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 240 tok/s | comfortable |
| M4 Max 128GB | 128GB | 58 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 29 tok/s | tight |
| M4 Pro 24GB | 24GB | 29 tok/s | tight |
| A100 PCIe 80 GB | 80GB | 293 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 590 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 141 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 117 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 113 tok/s | comfortable |