Skip to content

CosyVoice2-0.5B-S3Tokenizer

mlx-community/CosyVoice2-0.5B-S3Tokenizer
Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—

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
FunAudioLLM/CosyVoice2-0.5B (finetune)
Vendor
FunAudioLLM
Task
Text to speech
Quantisation
Not stated
Licence
apache-2.0
Downloads
0 in the last 30 days · 0 all time · 1 likes
Published
2025-07-02 · updated 2025-07-06 (1y ago)
Languages
en

Other MLX builds of FunAudioLLM/CosyVoice2-0.5B

Build Quantisation Weights Mac memory Downloads
S3TokenizerV2 — ≈ 495 MB 8 GB+ 12K
CosyVoice2-0.5B-4bit 4-bit ≈ 778 MB 8 GB+ 81
CosyVoice2-0.5B-8bit 8-bit ≈ 957 MB 8 GB+ 513
CosyVoice2-0.5B-fp16 fp16 ≈ 1.6 GB 8 GB+ 111
CosyVoice2-0.5B-S3Tokenizer (this one) — — — 0