coder3101 · First MLX build 2 Aug 2026
Skyfall-31B-v4.2-heretic
MLX
A 31B parameter model from coder3101, with 2 MLX builds, from 8-bit to fp16.
- Parameters
- 31B From Hugging Face
- Quantisation
- 8-bit Skyfall-31B-v4.2-heretic-mlx-8Bit
- Memory needed
- 40 GB Estimate, unified memory
- Download
- 33.3 GB Weights, estimated
- Downloads
- 150 This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 40 GB at 8-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/Skyfall-31B-v4.2-heretic-mlx-8BitMLX builds
2 on mlx-community| Skyfall-31B-v4.2-heretic-mlx-8Bit | 8-bit | 33.3 GB | 40 GB | 150 |
|---|---|---|---|---|
| Skyfall-31B-v4.2-heretic-mlx-fp16 | fp16 | 62.7 GB | 73 GB | 90 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.