Paraformer-zh needs about 0.8 GB of memory at Q8_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (Q4_K) to 0.4 GB (F16).
Paraformer-zh: 220M‑parameter Mandarin ASR in GGUF format
Paraformer-zh is a non‑autoregressive ASR model with 0.22 billion parameters. It supports Mandarin Chinese and mixed Chinese‑English recognition. The GGUF files are quantized for efficient inference on GPUs.
Good at
- 120x realtime GPU decoding
- Parallel full‑sequence generation
- Built‑in VAD and punctuation support
Limits
- No vision support
- No explicit language list provided
- Requires GPU for realtime performance
Best for
- Real‑time Mandarin transcription
- Mixed Chinese‑English speech recognition
- Low‑latency ASR pipelines
Who it’s for. Developers building Mandarin‑centric speech applications or integrating ASR into larger pipelines. The model is suitable for production‑ready deployments that need fast, parallel decoding.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| F16 | 0.4 GB | 1.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (0.13 GB file, ~0.6 GB memory at 8k context). For 12 GB VRAM, Q8_0 (0.24 GB file, ~0.8 GB memory). For 16 GB VRAM, F16 (0.44 GB file, ~1 GB memory). Estimates are approximate.
What GPU do you need for Paraformer-zh?
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 (0.4 GB file, about 1.0 GB in use).
Which Paraformer-zh quant should you choose?
Q8_0 (0.2 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 0.1 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 Paraformer-zh
How much VRAM does Paraformer-zh need?
About 0.8 GB at Q8_0 with an 8K context window. That is the 0.2 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 Paraformer-zh on an 8 GB GPU?
Yes, with F16: the 0.4 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Paraformer-zh GGUF?
It depends on the quant: Q4_K is 0.1 GB, Q8_0 is 0.2 GB, F16 is 0.4 GB.
Where can I download Paraformer-zh GGUF?
The files are on Hugging Face in the cstr/paraformer-zh-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 Paraformer-zh 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 Paraformer-zh on 8 GB VRAM?
Yes, the Q4_K quantization requires about 0.6 GB of VRAM at 8k context, well within an 8 GB budget.
Does Paraformer-zh support English only?
It supports mixed Chinese‑English recognition, but the primary focus is Mandarin Chinese.
Is there a license restriction?
The model is released under an "other" license; check the repository for details.