4-bit Open on Hugging Face
Parameters
32B
Weights (est.)
≈ 18.1 GB
Mac memory (est.)
24 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Olmo-3.1-32B-Instruct-4bit --prompt "Hello"
Details
- Base model
- allenai/Olmo-3.1-32B-Instruct (quantized)
- Vendor
- Ai2 · OLMo
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 494 in the last 30 days · 1.1K all time · 0 likes
- Published
- 2025-12-23 · updated 2025-12-23 (10mo ago)
- Languages
- en
- Tags
- olmo3
Other MLX builds of allenai/Olmo-3.1-32B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Olmo-3.1-32B-Instruct-4bit (this one) | 4-bit | ≈ 18.1 GB | 24 GB+ | 494 |
| Olmo-3.1-32B-Instruct-8bit | 8-bit | ≈ 34.2 GB | 48 GB+ | 97 |
| Olmo-3.1-32B-Instruct-bf16 | bf16 | ≈ 64.5 GB | 96 GB+ | 33 |