Cohere · First MLX build 14 Dec 2024
c4ai-command-r7b-12-2024
MLX
Text cc-by-nc-4.0
A 8B parameter text generation model from Cohere, with 5 MLX builds, from 3-bit to bf16.
- Parameters
- 8B From Hugging Face
- Quantisation
- bf16 c4ai-command-r7b-12-2024-bf16
- Memory needed
- 20 GB Estimate, unified memory
- Download
- 16.1 GB Weights, estimated
- Downloads
- 181 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 20 GB at bf16
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/c4ai-command-r7b-12-2024-bf16 --prompt "Hello"MLX builds
5 on mlx-community| c4ai-command-r7b-12-2024-3bit | 3-bit | 3.5 GB | 6 GB | 47 |
|---|---|---|---|---|
| c4ai-command-r7b-12-2024-4bit | 4-bit | 4.5 GB | 8 GB | 126 |
| c4ai-command-r7b-12-2024-6bit | 6-bit | 6.5 GB | 10 GB | 59 |
| c4ai-command-r7b-12-2024-8bit | 8-bit | 8.5 GB | 12 GB | 70 |
| c4ai-command-r7b-12-2024-bf16 | bf16 | 16.1 GB | 20 GB | 181 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.