6-bit Open on Hugging Face
Parameters
21B
Weights (est.)
≈ 17.0 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/context-1-MLX-6bit --prompt "Hello"
Details
- Base model
- chromadb/context-1 (quantized)
- Vendor
- chromadb
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- apache-2.0
- Downloads
- 32 in the last 30 days · 452 all time · 0 likes
- Published
- 2026-03-31 · updated 2026-03-31 (7mo ago)
- Languages
- en
- Tags
- gpt_oss, mixture-of-experts, 6bit, quantized, apple-silicon, agentic, retrieval, search, tool-calling, lm-studio
Other MLX builds of chromadb/context-1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| context-1-MLX-4bit | 4-bit | ≈ 11.8 GB | 16 GB+ | 36 |
| context-1-MLX-6bit (this one) | 6-bit | ≈ 17.0 GB | 24 GB+ | 32 |