karakuri-ai · First MLX build 11 Oct 2024
karakuri-lm-8x7b-instruct-v0.1
MLX
Text apache-2.0
A 47B parameter text generation model from karakuri-ai, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 47B From Hugging Face
- Quantisation
- Unstated karakuri-lm-8x7b-instruct-v0.1
- Memory needed
- 107 GB Estimate, unified memory
- Download
- 93.4 GB Weights, estimated
- Downloads
- 52 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 107 GB at Unstated
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/karakuri-lm-8x7b-instruct-v0.1 --prompt "Hello"MLX builds
3 on mlx-community| karakuri-lm-8x7b-instruct-v0.1-4bit | 4-bit | 26.3 GB | 32 GB | 31 |
|---|---|---|---|---|
| karakuri-lm-8x7b-instruct-v0.1-8bit | 8-bit | 49.6 GB | 58 GB | 26 |
| karakuri-lm-8x7b-instruct-v0.1 | Unstated | 93.4 GB | 107 GB | 52 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.