llm-jp-3-7.2b-instruct3-4bit
mlx-community/llm-jp-3-7.2b-instruct3-4bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
7.3B
Weights (est.)
≈ 4.1 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/llm-jp-3-7.2b-instruct3-4bit --prompt "Hello"
Details
- Base model
- llm-jp/llm-jp-3-7.2b-instruct3 (quantized)
- Vendor
- llm-jp
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 113 in the last 30 days · 374 all time · 0 likes
- Published
- 2025-02-07 · updated 2025-02-07 (1y ago)
- Languages
- en, ja
- Tags
- llama
Other MLX builds of llm-jp/llm-jp-3-7.2b-instruct3
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| llm-jp-3-7.2b-instruct3-4bit (this one) | 4-bit | ≈ 4.1 GB | 8 GB+ | 113 |
| llm-jp-3-7.2b-instruct3 | — | ≈ 14.6 GB | 24 GB+ | 98 |