5-bit Open on Hugging Face
Parameters
399B
Weights (est.)
≈ 274 GB
Mac memory (est.)
512 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-Large-Thinking-5bit --prompt "Hello"
Details
- Base model
- arcee-ai/Trinity-Large-Thinking (quantized)
- Vendor
- arcee-ai
- Task
- Text generation
- Quantisation
- 5-bit
- Licence
- apache-2.0
- Downloads
- 26 in the last 30 days · 603 all time · 0 likes
- Published
- 2026-04-02 · updated 2026-04-02 (7mo ago)
- Languages
- en, es, fr, de, it, pt, ru, ar, hi, ko, zh
- Tags
- afmoe, reasoning, agentic, tool-calling, thinking, custom_code
Other MLX builds of arcee-ai/Trinity-Large-Thinking
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Trinity-Large-Thinking-4bit | 4-bit | ≈ 224 GB | 256 GB+ | 34 |
| Trinity-Large-Thinking-5bit (this one) | 5-bit | ≈ 274 GB | 512 GB+ | 26 |