MLX Community · First MLX build 9 Jan 2024
dolphin-2.6-mistral-7b-dpo-laser
MLX
apache-2.0
A model, with 2 MLX builds at 4-bit.
- Parameters
- — Not published
- Quantisation
- 4-bit dolphin-2.6-mistral-7b-dpo-laser-4bit-mlx
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 36 This build, last 30 days
- Task
- —
- 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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/dolphin-2.6-mistral-7b-dpo-laser-4bit-mlxMLX builds
2 on mlx-community| dolphin-2.6-mistral-7b-dpo-laser-4bit-mlx | 4-bit | — | — | 36 |
|---|---|---|---|---|
| dolphin-2.6-mistral-7b-dpo-laser-mlx | Unstated | — | — | 27 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.