8-bit Open on Hugging Face
Parameters
249M
Weights (est.)
≈ 356 MB
Mac memory (est.)
8 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/dhara-250m-OptiQ-8bit --prompt "Hello"
Details
- Base model
- codelion/dhara-250m (quantized)
- Vendor
- codelion
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 68 in the last 30 days · 1.2K all time · 3 likes
- Published
- 2026-06-13 · updated 2026-07-12 (4mo ago)
- Languages
- en
- Tags
- dhara_ar, optiq, diffusion-llm, dhara, quantized, custom_code