Olmo 3.1 32B Think — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
The reasoning build of Olmo 3.1 32B: the same network and 65,536-token context as the Instruct model, post-trained to write out its reasoning before it answers. Fully open (data, code and checkpoints) under Apache-2.0.
Olmo 3.1 32B Think 在 Q4_K_M 下约需 20 GB 显存——量化权重加框架开销，不含 KV 缓存。在 Apple Silicon 上，这部分来自统一内存。
按量化级别的显存与速度
计算基准：NVIDIA RTX 4090 (24 GB)。包含 8K 上下文的 KV 缓存，因此数值高于上方的主数字。
| 量化 | 显存 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 12.8 GB | ~57 tok/s | 可运行 | |
| Q3_K_M 3.41 bpw | 16 GB | ~46 tok/s | 可运行 | |
| Q4_K_M 4.83 bpw | 21.7 GB | ~34 tok/s | 勉强 | |
| Q5_K_M 5.67 bpw | 25.1 GB | ~4 tok/s | 需卸载 | |
| Q6_K 6.56 bpw | 28.7 GB | ~4 tok/s | 需卸载 | |
| Q8_0 8.50 bpw | 36.5 GB | ~3 tok/s | 需卸载 | |
| F16 16.00 bpw | 66.7 GB | — | 放不下 |
黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型，详见 方法说明页. Olmo 3.1 32B Think 显存计算器 →
运行 Olmo 3.1 32B Think
目录中能运行 Olmo 3.1 32B Think 的最便宜 GPU 是 AMD Radeon RX 7900 XTX (24 GB).
或在 Vast.ai 比较，低至 $0.35/小时 (typical low · varies)
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
如何运行 Olmo 3.1 32B Think
安装 Ollama，然后运行：
ollama run olmo-3.1:32b-think规格
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- 参数量
- 32 Billion
- 上下文窗口
- 65,536
- 架构
- Dense transformer, 3:1 sliding-window (4,096) to full attention
- 提供商
- Ai2 (Allen Institute for AI)
- 许可证
- Apache-2.0
- Availability
- Weights downloadable
- Practical deployment
- Single consumer GPU
- 规格量化
- Q4_K_M
- 系统内存
- 32 GB
- 记录更新于
- 2026-11-11
- Runs with
- Ollama: supported source
Commercial use permitted. No usage restrictions beyond attribution.
质量与使用场景
评分由模型作者或独立评测方发布——衡量质量而非吞吐量，并非我们实测。
Olmo 3 的其他尺寸
Olmo 3.1 32B Think — 常见问题
How much VRAM does Olmo 3.1 32B Think need?
About 20 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Olmo 3.1 32B Think run on an RTX 4090 (24 GB)?
Yes. Olmo 3.1 32B Think needs about 20 GB at Q4_K_M, inside a 24 GB card, at an estimated 34 tokens/sec.
How do I run Olmo 3.1 32B Think locally?
Install Ollama and run `ollama run olmo-3.1:32b-think`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Olmo 3 come in?
Olmo 3 7B (5 GB), Olmo 3 32B (20 GB), Olmo 3.1 32B Instruct (20 GB), Olmo 3.1 32B Think (20 GB), Olmo Hybrid 7B (5 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.