Ai2 · First MLX build 24 Dec 2025
Olmo-3.1-32B-Think
MLX
Text apache-2.0
A 32B parameter text generation model from Ai2, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 32B From Hugging Face
- Quantisation
- 4-bit Olmo-3.1-32B-Think-4bit
- Memory needed
- 23 GB Estimate, unified memory
- Download
- 18.1 GB Weights, estimated
- Downloads
- 525 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 23 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Olmo-3.1-32B-Think-4bit --prompt "Hello"MLX builds
3 on mlx-community| Olmo-3.1-32B-Think-4bit | 4-bit | 18.1 GB | 23 GB | 525 |
|---|---|---|---|---|
| Olmo-3.1-32B-Think-8bit | 8-bit | 34.2 GB | 41 GB | 410 |
| Olmo-3.1-32B-Think-bf16 | bf16 | 64.5 GB | 75 GB | 25 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.