Allen AI · 32B · 密集（Dense）
Fully open research model by Allen AI 看看你的 GPU 或 Mac 跑不跑得動 OLMo 2 32B——最低 17.9 GB，建議 29.8 GB。
2025-034K context
| 量化 | 位元 | VRAM | 品質 | 狀態 |
|---|---|---|---|---|
| Q2_K | 2 | 10.7 GB | low | — |
| Q3_K_M | 3 | 14.8 GB | moderate | — |
| Q4_K_M | 4 | 16.9 GB | good | — |
| Q5_K_M | 5 | 21 GB | good | — |
| Q6_K | 6 | 25.1 GB | excellent | — |
| Q8_0 | 8 | 33.3 GB | excellent | — |
| F16 | 16 | 66.1 GB | lossless | — |
Can I run OLMo 2 32B locally?
- Can I run OLMo 2 32B locally?
- OLMo 2 32B needs about 17.9 GB of memory at a minimum and 29.8 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does OLMo 2 32B need?
- At Q4_K_M, OLMo 2 32B uses about 16.9 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.