Olmo-3-7B-Instruct
by allenai
528K params · text-generation · 120 likes · 102.8k downloads
Olmo-3-7B-Instruct is a 528K parameter model. At Q4 quantization it requires 0GB of VRAM. It runs comfortably on GeForce RTX 4090 (2484935 tok/s), GeForce RTX 5090 (3726456 tok/s), M4 Max 128GB (909338 tok/s).
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Public AI |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 2484935 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 3726456 tok/s | comfortable |
| M4 Max 128GB | 128GB | 909338 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 454669 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 454669 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 4552749 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 9156976 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 2197053 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 1816860 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 1763565 tok/s | comfortable |