NeverSleep · First MLX build 13 Oct 2024
MiquMaid-v3-70B
MLX
cc-by-nc-4.0
A 69B parameter model from NeverSleep, with one MLX build at 8-bit.
- Parameters
- 69B From Hugging Face
- Quantisation
- 8-bit MiquMaid-v3-70B
- Memory needed
- 84 GB Estimate, unified memory
- Download
- 73.3 GB Weights, estimated
- Downloads
- 15 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 84 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/MiquMaid-v3-70BMLX builds
1 on mlx-community| MiquMaid-v3-70B | 8-bit | 73.3 GB | 84 GB | 15 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.