4-bit Open on Hugging Face
Parameters
2.4B
Weights (est.)
≈ 1.3 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/Kumru-2B-4bit --prompt "Hello"
Details
- Base model
- vngrs-ai/Kumru-2B (quantized)
- Vendor
- vngrs-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 94 in the last 30 days · 1.2K all time · 0 likes
- Published
- 2025-10-15 · updated 2025-10-15 (1y ago)
- Languages
- tr
- Tags
- mistral
Other MLX builds of vngrs-ai/Kumru-2B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Kumru-2B-4bit (this one) | 4-bit | ≈ 1.3 GB | 8 GB+ | 94 |
| Kumru-2B-6bit | 6-bit | ≈ 1.9 GB | 8 GB+ | 17 |
| Kumru-2B-8bit | 8-bit | ≈ 2.5 GB | 8 GB+ | 27 |
| Kumru-2B-bf16 | bf16 | ≈ 4.8 GB | 8 GB+ | 35 |