gemma-7b-it
by google
8.5B params · text-generation · 1.2k likes · 19.9k downloads
gemma-7b-it is a 8.5B parameter model. At Q4 quantization it requires 4GB of VRAM. It runs comfortably on GeForce RTX 4090 (153 tok/s), GeForce RTX 5090 (230 tok/s), M4 Max 128GB (56 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Featherless |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 153 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 230 tok/s | comfortable |
| M4 Max 128GB | 128GB | 56 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 28 tok/s | tight |
| M4 Pro 24GB | 24GB | 28 tok/s | tight |
| A100 PCIe 80 GB | 80GB | 281 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 566 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 135 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 112 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 109 tok/s | comfortable |