MLX Community · First MLX build 6 Dec 2023
Llama-2-7b-chat
MLX
Text llama2
A text generation model, with 2 MLX builds at 4-bit.
- Parameters
- — Not published
- Quantisation
- Unstated Llama-2-7b-chat-mlx
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 2.4K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/Llama-2-7b-chat-mlx --prompt "Hello"MLX builds
2 on mlx-community| Llama-2-7b-chat-mlx | Unstated | — | — | 2.4K |
|---|---|---|---|---|
| Llama-2-7b-chat-4-bit | 4-bit | — | — | 109 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.