4-bit Open on Hugging Face
Parameters
4.0B
Weights (est.)
≈ 2.3 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/Mellum-4b-base-4bit --prompt "Hello"
Details
- Base model
- JetBrains/Mellum-4b-base (quantized)
- Vendor
- JetBrains
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 98 in the last 30 days · 1.6K all time · 3 likes
- Published
- 2025-06-28 · updated 2025-06-28 (1y ago)
- Tags
- llama, code, model-index
Other MLX builds of JetBrains/Mellum-4b-base
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Mellum-4b-base-4bit (this one) | 4-bit | ≈ 2.3 GB | 8 GB+ | 98 |
| Mellum-4b-base-8bit | 8-bit | ≈ 4.3 GB | 8 GB+ | 46 |
| Mellum-4b-base | — | ≈ 8.0 GB | 16 GB+ | 68 |