4-bit Open on Hugging Face
Parameters
31B
Weights (est.)
≈ 17.2 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/MiroThinker-v1.5-30B --prompt "Hello"
Details
- Base model
- miromind-ai/MiroThinker-v1.5-30B (quantized)
- Vendor
- miromind-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 31 in the last 30 days · 753 all time · 3 likes
- Published
- 2026-01-24 · updated 2026-01-24 (9mo ago)
- Languages
- en
- Tags
- qwen3_moe, agent, open-source, miromind, deep-research, mlx-my-repo