Fun-ASR-MLT-Nano-2512 needs about 1.9 GB of memory at Q8_0 (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.9 GB (Q4_K) to 2.0 GB (F16).
800M‑parameter multilingual ASR model
Fun-ASR-MLT-Nano-2512 is an 800M‑parameter multilingual speech recognition model. It covers 31 languages with a focus on East and Southeast Asian languages. The model is part of the FunASR ecosystem and is quantised for use with llama.cpp.
Good at
- Multilingual speech recognition
- East/Southeast Asian language support
- Compact 800M‑parameter size
Limits
- No vision support
- No CTC path
- License is other
Best for
- Transcribing multilingual audio
- Language‑controlled ASR
- Low‑latency inference
Who it’s for. Developers building multilingual speech recognition applications who need a compact model with broad language coverage. The model is suitable for edge deployments where memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 1.3 GB | 1.9 GB | Fits | Get file → | |
| F16 | 2.0 GB | 2.7 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_K quant is recommended (file size 0.9 GB, estimated 1.5 GB at 8 k context). If more VRAM is available, Q8_0 (1.27 GB, 1.9 GB) or F16 (1.98 GB, 2.7 GB) can be used for higher precision.
What GPU do you need for Fun-ASR-MLT-Nano-2512?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F16 (2.0 GB file, about 2.7 GB in use).
Which Fun-ASR-MLT-Nano-2512 quant should you choose?
Q8_0 (1.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q4_K at 0.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Fun-ASR-MLT-Nano-2512
How much VRAM does Fun-ASR-MLT-Nano-2512 need?
About 1.9 GB at Q8_0 with an 8K context window. That is the 1.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Fun-ASR-MLT-Nano-2512 on an 8 GB GPU?
Yes, with F16: the 2.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Fun-ASR-MLT-Nano-2512 GGUF?
It depends on the quant: Q4_K is 0.9 GB, Q8_0 is 1.3 GB, F16 is 2.0 GB.
Where can I download Fun-ASR-MLT-Nano-2512 GGUF?
The files are on Hugging Face in the cstr/funasr-mlt-nano-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Fun-ASR-MLT-Nano-2512 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the Q4_K quantised file (0.9 GB) uses about 1.5 GB of VRAM at 8 k context, fitting within 8 GB.
Does this model support speaker diarization?
No, speaker diarization is not supported in the current GGUF release.
What languages are supported?
The model supports 31 languages, with emphasis on East and Southeast Asian languages.