4-bit Open on Hugging Face
Parameters
35B
Weights (est.)
≈ 20.4 GB
Mac memory (est.)
32 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/XYZ-Aquila-mini-OptiQ-4bit --prompt "Hello"
Details
- Base model
- XYZAILab/XYZ-Aquila-mini (quantized)
- Vendor
- XYZAILab
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 84 in the last 30 days · 705 all time · 4 likes
- Published
- 2026-07-25 · updated 2026-09-15 (1mo ago)
- Tags
- qwen3_5_moe, optiq, mixed-precision, qwen3.6, agentic-search