Skip to content

Dia-1.6B-fp16

mlx-community/Dia-1.6B-fp16
fp16 Open on Hugging Face
Parameters
1.6B
Weights (est.)
≈ 3.2 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
nari-labs/Dia-1.6B (finetune)
Vendor
nari-labs
Task
Text to speech
Quantisation
fp16
Licence
apache-2.0
Downloads
606 in the last 30 days · 2.6K all time · 3 likes
Published
2025-04-27 · updated 2025-04-27 (1y ago)
Languages
en

Other MLX builds of nari-labs/Dia-1.6B

Build Quantisation Weights Mac memory Downloads
Dia-1.6B-fp16 (this one) fp16 ≈ 3.2 GB 8 GB+ 606
Dia-1.6B-4bit 4-bit ≈ 3.2 GB 8 GB+ 139
Dia-1.6B-6bit 6-bit ≈ 3.2 GB 8 GB+ 92
Dia-1.6B-3bit 3-bit ≈ 3.2 GB 8 GB+ 23
Dia-1.6B — ≈ 6.4 GB 16 GB+ 1.4K