ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit
mlx-community/ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit
Text generation · mlx
8-bit Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 8.5 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/ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit --prompt "Hello"
Details
- Base model
- DataPilot/ArrowCanaria-Llama-8B-RL-v0.1 (quantized)
- Vendor
- DataPilot
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- llama3.3
- Downloads
- 21 in the last 30 days · 121 all time · 0 likes
- Published
- 2026-03-27 · updated 2026-03-27 (7mo ago)
- Languages
- ja
- Tags
- llama
Other MLX builds of DataPilot/ArrowCanaria-Llama-8B-RL-v0.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| ArrowCanaria-Llama-8B-RL-v0.1-MLX-4bit | 4-bit | ≈ 4.5 GB | 8 GB+ | 29 |
| ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit (this one) | 8-bit | ≈ 8.5 GB | 16 GB+ | 21 |