Skip to content

dolphin-2.9.4-llama3.1-8b

mlx-community/dolphin-2.9.4-llama3.1-8b
Uncategorised · mlx
Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 16.1 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.

Details

Base model
dphn/dolphin-2.9.4-llama3.1-8b (finetune)
Vendor
dphn
Task
Uncategorised
Quantisation
Not stated
Licence
llama3.1
Downloads
35 in the last 30 days · 535 all time · 1 likes
Published
2024-10-21 · updated 2024-10-21 (2y ago)
Tags
llama, generated_from_trainer

Other MLX builds of dphn/dolphin-2.9.4-llama3.1-8b

Build Quantisation Weights Mac memory Downloads
dolphin-2.9.4-llama3.1-8b-4bit 4-bit ≈ 4.5 GB 8 GB+ 88
dolphin-2.9.4-llama3.1-8b-8bit 8-bit ≈ 8.5 GB 16 GB+ 136
dolphin-2.9.4-llama3.1-8b (this one) — ≈ 16.1 GB 24 GB+ 35