6-bit Open on Hugging Face
Parameters
12B
Weights (est.)
≈ 10.0 GB
Mac memory (est.)
16 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/Rivermind-Lux-12B-v1-6bit --prompt "Hello"
Details
- Base model
- TheDrummer/Rivermind-Lux-12B-v1 (quantized)
- Vendor
- TheDrummer
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- —
- Downloads
- 14 in the last 30 days · 125 all time · 0 likes
- Published
- 2025-06-06 · updated 2025-06-06 (1y ago)
- Tags
- mistral
Other MLX builds of TheDrummer/Rivermind-Lux-12B-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Rivermind-Lux-12B-v1-4bit | 4-bit | ≈ 6.9 GB | 16 GB+ | 18 |
| Rivermind-Lux-12B-v1-6bit (this one) | 6-bit | ≈ 10.0 GB | 16 GB+ | 14 |
| Rivermind-Lux-12B-v1-8bit | 8-bit | ≈ 13.0 GB | 24 GB+ | 20 |
| Rivermind-Lux-12B-v1-bf16 | bf16 | ≈ 24.5 GB | 32 GB+ | 37 |