CO

Confucius4 R2T2

ConfuciusGGUF by davidxifengUpdated 2026-09-19
Download on Hugging Face
Parameters—
Context—
Layers—
Architectureaudiocpp
Smallest quant2.5 GB
Quick answer

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 2 quants, from 2.5 GB (Q8_0) to 4.1 GB (F16).

Low‑latency, append‑only streaming ASR for Chinese and English

Confucius4 R2T2 is a real‑time speech recognition model built on Qwen3‑ASR. It delivers low latency (200‑600 ms) and high accuracy while committing output permanently. The model supports configurable decoding chunks from 80 ms to 2 s.

Good at

  • Stable, append‑only streaming output
  • Low latency with high accuracy
  • Configurable chunking for latency/accuracy trade‑offs

Limits

  • Requires 3.3 GB VRAM for Q8_0 at 8 k context
  • Only supports Chinese and English
  • No vision or multimodal capabilities

Best for

  • Real‑time live captioning
  • LLM agents needing instant text
  • Simultaneous speech translation

Who it’s for. Engineers and developers building real‑time transcription or downstream NLP pipelines that require stable, low‑latency text output. Suitable for applications where text must be processed immediately without revisions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_02.5 GB 3.3 GB
Fits Get file →
F164.1 GB 5.1 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (2.48 GB file, ~3.3 GB memory). If more VRAM is available, F16 (4.09 GB file, ~5.1 GB memory) offers higher precision. Memory estimates are approximate.

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 (4.1 GB file, about 5.1 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureaudiocpp

Source

Quantized bydavidxifeng
FamilyConfucius
Licenseother
Downloads (HF)66,663
Last updated2026-09-19

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 4.1 GB file needs about 5.1 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: Q8_0 is 2.5 GB, F16 is 4.1 GB.

Where can I download Confucius4 R2T2 GGUF?

The files are on Hugging Face in the davidxifeng/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 Q8_0 quantization requires about 3.3 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does the model support other languages besides 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, Confucius4 R2T2 is a pure ASR model with no vision support.

Other GGUFs of Confucius4-R2T2

More from davidxifeng

All by davidxifeng →

More Confucius models

All Confucius →