Skip to content

Fun-ASR-Nano-2512-fp16

mlx-community/Fun-ASR-Nano-2512-fp16
Speech recognition · mlx-audio-plus
fp16 Open on Hugging Face
Parameters
985M
Weights (est.)
≈ 2.0 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
FunAudioLLM/Fun-ASR-Nano-2512 (finetune)
Vendor
FunAudioLLM
Task
Speech recognition
Quantisation
fp16
Licence
—
Downloads
122 in the last 30 days · 1.5K all time · 2 likes
Published
2025-12-16 · updated 2025-12-16 (11mo ago)
Languages
multilingual
Tags
mlx-audio-plus, funasr, speech-recognition, speech-to-text

Other MLX builds of FunAudioLLM/Fun-ASR-Nano-2512

Build Quantisation Weights Mac memory Downloads
Fun-ASR-Nano-2512-4bit 4-bit ≈ 1.3 GB 8 GB+ 100
Fun-ASR-Nano-2512-8bit 8-bit ≈ 1.5 GB 8 GB+ 167
Fun-ASR-Nano-2512-fp16 (this one) fp16 ≈ 2.0 GB 8 GB+ 122