4-bit Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 4.5 GB
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/Llama-3-Karamaru-v1-4bit --prompt "Hello"
Details
- Base model
- SakanaAI/Llama-3-Karamaru-v1 (quantized)
- Vendor
- SakanaAI
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama3
- Downloads
- 20 in the last 30 days · 365 all time · 0 likes
- Published
- 2025-04-01 · updated 2025-04-01 (1y ago)
- Languages
- ja
- Tags
- llama
Other MLX builds of SakanaAI/Llama-3-Karamaru-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Llama-3-Karamaru-v1-4bit (this one) | 4-bit | ≈ 4.5 GB | 8 GB+ | 20 |
| Llama-3-Karamaru-v1-8bit | 8-bit | ≈ 8.5 GB | 16 GB+ | 17 |
| Llama-3-Karamaru-v1 | — | ≈ 16.1 GB | 24 GB+ | 29 |