confucius4 r2t2 needs about 3.3 GB of memory at Q8_0 (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.5 GB (Q4_K) to 4.7 GB (F16).
Real-time, low‑latency ASR model based on Qwen3-ASR
Confucius4‑R2T2 is a streaming Automatic Speech Recognition model that emits stable, append‑only text. It supports decoding chunks from 80 ms to 2 s and maintains offline accuracy. The model is optimized for Chinese and English.
Good at
- Low‑latency real‑time transcription
- Stable, non‑revising output
- Configurable chunking for latency/accuracy trade‑offs
Limits
- No vision support
- License is other, not open source
- No explicit context length info
Best for
- Real‑time live captioning
- Subtitling for streaming media
- LLM agents that need instant text
Who it’s for. Developers building real‑time speech‑to‑text pipelines or downstream NLP applications that require stable, low‑latency transcription. The model is suitable for Chinese and English language use cases.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q8_0 | 2.5 GB | 3.3 GB | Fits | Get file → | |
| F16 | 4.7 GB | 5.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (1.49 GB, ~2.2 GB RAM). For 12 GB VRAM, Q8_0 (2.51 GB, ~3.3 GB RAM). If you have 16 GB VRAM or more, F16 (4.7 GB, ~5.8 GB RAM) gives the highest precision.
What GPU do you need for confucius4 r2t2?
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 Q8_0 (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (4.7 GB file, about 5.8 GB in use).
Which confucius4 r2t2 quant should you choose?
Q8_0 (2.5 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 1.5 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 confucius4 r2t2
How much VRAM does confucius4 r2t2 need?
About 3.3 GB at Q8_0 with an 8K context window. That is the 2.5 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 confucius4 r2t2 on an 8 GB GPU?
Yes, with F16: the 4.7 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of confucius4 r2t2 GGUF?
It depends on the quant: Q4_K is 1.5 GB, Q8_0 is 2.5 GB, F16 is 4.7 GB.
Where can I download confucius4 r2t2 GGUF?
The files are on Hugging Face in the cstr/confucius4-r2t2-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 confucius4 r2t2 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 Confucius4‑R2T2 on 8 GB VRAM?
Yes, the Q4_K quantized model is 1.49 GB and requires about 2.2 GB of RAM at 8 k context, fitting comfortably on 8 GB VRAM.
Does the model support languages other than Chinese and English?
The model is optimized for Chinese and English; other languages are not guaranteed to perform well.
Is there a vision or multimodal version of this model?
No, the model is purely audio‑to‑text and does not support vision inputs.