8-bit Open on Hugging Face
Parameters
26B
Weights (est.)
≈ 27.8 GB
Mac memory (est.)
48 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/Trinity-Mini-8bit --prompt "Hello"
Details
- Base model
- arcee-ai/Trinity-Mini (quantized)
- Vendor
- arcee-ai
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 38 in the last 30 days · 386 all time · 0 likes
- Published
- 2025-12-02 · updated 2025-12-02 (11mo ago)
- Languages
- en, es, fr, de, it, pt, ru, ar, hi, ko, zh
- Tags
- afmoe, custom_code
Other MLX builds of arcee-ai/Trinity-Mini
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Trinity-Mini-4bit | 4-bit | ≈ 14.7 GB | 24 GB+ | 84 |
| Trinity-Mini-5bit | 5-bit | ≈ 18.0 GB | 24 GB+ | 33 |
| Trinity-Mini-6bit | 6-bit | ≈ 21.2 GB | 32 GB+ | 32 |
| Trinity-Mini-8bit (this one) | 8-bit | ≈ 27.8 GB | 48 GB+ | 38 |