Ai2 · First MLX build 20 Nov 2025
Olmo-3-1025-7B
MLX
Text apache-2.0
A 7.3B parameter text generation model from Ai2, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 7.3B From Hugging Face
- Quantisation
- Unstated Olmo-3-1025-7B-bfloat16
- Memory needed
- 19 GB Estimate, unified memory
- Download
- 14.6 GB Weights, estimated
- Downloads
- 46 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 19 GB at Unstated
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-3-1025-7B-bfloat16 --prompt "Hello"MLX builds
4 on mlx-community| Olmo-3-1025-7B-4bit | 4-bit | 4.1 GB | 7 GB | 35 |
|---|---|---|---|---|
| Olmo-3-1025-7B-6bit | 6-bit | 5.9 GB | 9 GB | 21 |
| Olmo-3-1025-7B-8bit | 8-bit | 7.8 GB | 11 GB | 27 |
| Olmo-3-1025-7B-bfloat16 | Unstated | 14.6 GB | 19 GB | 46 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.