Sao10K · First MLX build 20 Oct 2024
Fimbulvetr-11B-v2
MLX
cc-by-nc-4.0
A 11B parameter model from Sao10K, with 2 MLX builds at 8-bit.
- Parameters
- 11B From Hugging Face
- Quantisation
- 8-bit Fimbulvetr-11B-v2-8bit
- Memory needed
- 15 GB Estimate, unified memory
- Download
- 11.4 GB Weights, estimated
- Downloads
- 58 This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 15 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/Fimbulvetr-11B-v2-8bitMLX builds
2 on mlx-community| Fimbulvetr-11B-v2-8bit | 8-bit | 11.4 GB | 15 GB | 58 |
|---|---|---|---|---|
| Fimbulvetr-11B-v2 | Unstated | 21.5 GB | 26 GB | 33 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.