TheDrummer · First MLX build 28 May 2025
UnslopNemo-12B-v4.1
MLX
A 12B parameter model from TheDrummer, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 12B From Hugging Face
- Quantisation
- 4-bit UnslopNemo-12B-v4.1-4bit
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.9 GB Weights, estimated
- Downloads
- 44 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 10 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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/UnslopNemo-12B-v4.1-4bitMLX builds
3 on mlx-community| UnslopNemo-12B-v4.1-4bit | 4-bit | 6.9 GB | 10 GB | 44 |
|---|---|---|---|---|
| UnslopNemo-12B-v4.1-8bit | 8-bit | 13.0 GB | 17 GB | 28 |
| UnslopNemo-12B-v4.1-bf16 | bf16 | 24.5 GB | 30 GB | 20 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.