vngrs-ai · First MLX build 15 Oct 2025
Kumru-2B
MLX
Text apache-2.0
A 2.4B parameter text generation model from vngrs-ai, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 2.4B From Hugging Face
- Quantisation
- 4-bit Kumru-2B-4bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.3 GB Weights, estimated
- Downloads
- 73 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Kumru-2B-4bit --prompt "Hello"MLX builds
4 on mlx-community| Kumru-2B-4bit | 4-bit | 1.3 GB | 4 GB | 73 |
|---|---|---|---|---|
| Kumru-2B-6bit | 6-bit | 1.9 GB | 5 GB | 17 |
| Kumru-2B-8bit | 8-bit | 2.5 GB | 5 GB | 27 |
| Kumru-2B-bf16 | bf16 | 4.8 GB | 8 GB | 35 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.