4-bit Open on Hugging Face
Parameters
8.3B
Weights (est.)
≈ 4.7 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/rnj-1-instruct-4bit --prompt "Hello"
Details
- Base model
- EssentialAI/rnj-1-instruct (quantized)
- Vendor
- EssentialAI
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 47 in the last 30 days · 542 all time · 0 likes
- Published
- 2025-12-08 · updated 2025-12-20 (10mo ago)
- Tags
- gemma3_text
Other MLX builds of EssentialAI/rnj-1-instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| rnj-1-instruct-4bit (this one) | 4-bit | ≈ 4.7 GB | 8 GB+ | 47 |
| rnj-1-instruct-6bit | 6-bit | ≈ 6.8 GB | 16 GB+ | 24 |
| rnj-1-instruct-8bit | 8-bit | ≈ 8.8 GB | 16 GB+ | 31 |
| rnj-1-instruct-bfloat16 | — | ≈ 16.6 GB | 24 GB+ | 24 |