Gemma-4-31B-IT-NVFP4
by nvidia
20.9B params · text-generation · 512 likes · 1.6M downloads
Gemma-4-31B-IT-NVFP4 is a 20.9B parameter model. At Q4 quantization it requires 10GB of VRAM. It runs comfortably on GeForce RTX 4090 (62 tok/s), GeForce RTX 5090 (94 tok/s), A100 PCIe 80 GB (115 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Featherless |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 62 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 | 231 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 |