4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/openchat-3.5-0106-4bit-mlx --prompt "Hello"
Details
- Base model
- mistralai/Mistral-7B-v0.1 (finetune) · Mistral 7B v0.1 on the radar →
- Vendor
- Mistral
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 108 in the last 30 days · 731 all time · 0 likes
- Published
- 2024-01-15 · updated 2024-01-16 (2y ago)
- Tags
- mistral, openchat, C-RLFT
Other MLX builds of mistralai/Mistral-7B-v0.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| OpenHermes-2.5-Mistral-7B-4bit-mlx | 4-bit | ≈ 4.3 GB | 8 GB+ | 97 |
| Nous-Hermes-2-Mistral-7B-DPO-4bit-MLX | 4-bit | ≈ 4.3 GB | 8 GB+ | 67 |
| Hermes-2-Pro-Mistral-7B-4bit | 4-bit | ≈ 4.3 GB | 8 GB+ | 199 |
| Hermes-2-Pro-Mistral-7B-8bit | 8-bit | ≈ 7.8 GB | 16 GB+ | 283 |
| openchat-3.5-0106-4bit-mlx (this one) | 4-bit | — | — | 108 |
| openchat-3.5-1210-7b-mlx | — | — | — | 47 |
| openchat-3.5-0106 | — | — | — | 45 |
| garten2-7b-4bit-mlx | 4-bit | — | — | 37 |
| BB-L-01-7B-mlx-4bit | 4-bit | — | — | 31 |
| zephyr-7b-sft-lora-fused-mlx | — | — | — | 23 |