Skip to content

dolphin-2.9.3-Yi-1.5-34B-32k-4bit

mlx-community/dolphin-2.9.3-Yi-1.5-34B-32k-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
5.4B
Weights (est.)
≈ 4.6 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-1.5-34B-32k
Vendor
01.AI · Yi
Task
Uncategorised
Quantisation
4-bit
Licence
apache-2.0
Downloads
15 in the last 30 days · 302 all time · 0 likes
Published
2024-06-23 · updated 2024-06-23 (2y ago)
Tags
llama, generated_from_trainer, axolotl

Other MLX builds of 01-ai/Yi-1.5-34B-32k

Build Quantisation Weights Mac memory Downloads
dolphin-2.9.3-Yi-1.5-34B-32k-2bit 2-bit ≈ 2.8 GB 8 GB+ 10
dolphin-2.9.3-Yi-1.5-34B-32k-4bit (this one) 4-bit ≈ 4.6 GB 8 GB+ 15
dolphin-2.9.3-Yi-1.5-34B-32k-8bit 8-bit ≈ 11.3 GB 16 GB+ 16