// FunAudioLLM speech · Speech-to-text
Fun-ASR-MLT-Nano-2512: VRAM & local deployment
Speech-to-text model published by Alibaba Tongyi Lab.
released 2025-12-15licence: Commercial OKmemory figures are estimates
01Specs
| Publisher | Alibaba Tongyi Lab · FunAudioLLM |
|---|---|
| Family / series | FunAudioLLM speech · Fun-ASR-MLT-Nano |
| Type | Speech-to-text (automatic-speech-recognition) |
| Parameters | not stated in official metadata |
| Licence | Apache-2.0 · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed. |
| Released | 2025-12-15 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Speech models are small; the weight size is close to the total memory needed.
No estimate: the official metadata does not give a parameter count. Check the model card for tested hardware.
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
04Official repositories & quantised builds
1 official repo(s) from FunAudioLLM.
05Other FunAudioLLM speech models
All 5 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| Fun-ASR-Nano-2512-hf | 830M | 1.1 GB | 2026-05-24 |
| Fun-CosyVoice3-0.5B-2512 | 500M | 0.8 GB | 2025-12-11 |
| CosyVoice2-0.5B | 500M | 0.8 GB | 2025-07-29 |
| SenseVoiceSmall | — | — | 2024-07-03 |
06Sources
Data checked 2026-08-05. Parameters, context and licence are copied from the official repository; memory figures are our estimates.