Fun-ASR Nano needs about 1.1 GB of memory at Q4_K_M (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.6 GB (Q4_K_M) to 1.7 GB (F16).
Fun-ASR Nano – compact, real‑time speech recognition in 31 languages
Fun-ASR Nano is a 0.83 billion‑parameter end‑to‑end ASR model. It runs as a single binary via llama.cpp / GGUF and includes built‑in VAD. The model supports 31 languages and 7 Chinese dialects, with strong performance in noisy, far‑field scenarios.
Good at
- Low‑latency real‑time transcription
- Multi‑language support (31 languages)
- Far‑field high‑noise recognition
Limits
- No GPU required, but no streaming or timestamps
- No built‑in long‑form chunking
- No vision or translation capabilities
Best for
- Edge devices needing on‑device ASR
- Real‑time transcription in noisy environments
- Multilingual voice assistants
Who it’s for. Developers building on‑device speech interfaces or edge AI solutions that require real‑time transcription without GPU support. The model is suitable for applications in education, finance, and industrial settings where accurate, low‑latency ASR is needed.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.6 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q6_K | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.9 GB | 1.5 GB | Fits | Get file → | |
| BF16 | 1.7 GB | 2.4 GB | Fits | Get file → | |
| F16 | 1.7 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.56 GB, ~1.1 GB VRAM at 8k context). For 12 GB VRAM, Q5_K_M (0.63 GB, ~1.2 GB VRAM) or Q6_K (0.69 GB, ~1.3 GB VRAM) are suitable. For larger memory budgets, Q8_0, BF16 or F16 provide higher precision but require more VRAM.
What GPU do you need for Fun-ASR Nano?
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 BF16 (1.7 GB file, about 2.4 GB in use).
Which Fun-ASR Nano quant should you choose?
Q4_K_M is the usual starting point for Fun-ASR Nano: it balances file size and quality well. Here it is a 0.6 GB file.
The Q8_0 file is 0.9 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Fun-ASR Nano
How much VRAM does Fun-ASR Nano need?
About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.6 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 Nano on an 8 GB GPU?
Yes, with BF16: the 1.7 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Fun-ASR Nano GGUF?
It depends on the quant: Q4_K_M is 0.6 GB, Q5_K_M is 0.6 GB, Q6_K is 0.7 GB, Q8_0 is 0.9 GB, BF16 is 1.7 GB, F16 is 1.7 GB.
Where can I download Fun-ASR Nano GGUF?
The files are on Hugging Face in the handy-computer/Fun-ASR-Nano-2512-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 Nano 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 Fun-ASR Nano on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 1.1 GB VRAM at 8k context, which fits within an 8 GB budget.
Does Fun-ASR Nano support streaming inference?
No, the model does not provide built‑in streaming or timestamps; it processes entire WAV files.
What languages does Fun-ASR Nano cover?
It covers 31 languages, including English, Chinese, Japanese, and 7 Chinese dialects such as Wu and Cantonese.