Llama-3-Aplite-Instruct-4x8B-MoE-4bit
mlx-community/Llama-3-Aplite-Instruct-4x8B-MoE-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
25B
Weights (est.)
≈ 14.0 GB
Mac memory (est.)
24 GB+
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/Llama-3-Aplite-Instruct-4x8B-MoE-4bit --prompt "Hello"
Details
- Base model
- meta-llama/Meta-Llama-3-8B-Instruct (finetune) · Meta Llama 3 8B Instruct on the radar →
- Vendor
- Meta · Llama
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama3
- Downloads
- 54 in the last 30 days · 558 all time · 0 likes
- Published
- 2024-04-26 · updated 2024-04-26 (2y ago)
- Languages
- en
- Tags
- mixtral, facebook, meta, pytorch, llama, llama-3, code