Skip to content

dolphin-2.9.1-yi-9b-4bit

mlx-community/dolphin-2.9.1-yi-9b-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
8.8B
Weights (est.)
≈ 5.0 GB
Mac memory (est.)
8 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.

Details

Base model
01-ai/Yi-1.5-9B (finetune)
Vendor
01.AI · Yi
Task
Uncategorised
Quantisation
4-bit
Licence
apache-2.0
Downloads
8 in the last 30 days · 209 all time · 0 likes
Published
2024-05-18 · updated 2024-05-18 (2y ago)
Tags
llama, generated_from_trainer

Other MLX builds of 01-ai/Yi-1.5-9B

Build Quantisation Weights Mac memory Downloads
dolphin-2.9.1-yi-9b-2bit 2-bit ≈ 2.8 GB 8 GB+ 25
dolphin-2.9.1-yi-9b-4bit (this one) 4-bit ≈ 5.0 GB 8 GB+ 8
dolphin-2.9.1-yi-9b-8bit 8-bit ≈ 9.4 GB 16 GB+ 13