Confucius4 T3PO needs about 14.2 GB of memory at Q6_K (a 12.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 10.5 GB (Q5_K_M) to 29.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Confucius4 T3PO – 15‑billion‑parameter Chinese–English streaming translation model
Confucius4 T3PO is a 15‑billion‑parameter text‑to‑text simultaneous translation model based on the Qwen2 architecture. It supports fine‑grained streaming input and real‑time READ/WRITE decisions, enabling low‑latency translation. The model is released under the Apache‑2.0 license.
Good at
- Fine‑grained streaming translation
- Adjustable latency modes
- Retained instruction‑following ability
Limits
- No native speech input
- Large VRAM requirement for higher quality quants
- No vision support
Best for
- Live simultaneous interpretation
- Real‑time subtitle generation
- Low‑latency translation in streaming apps
Who it’s for. Developers building real‑time translation services or streaming applications that require Chinese–English bidirectional translation. The model is suitable for teams that can run llama.cpp and manage the required VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 10.5 GB | 12.6 GB | Too big | Get file → | |
| Q6_K | 12.1 GB | 14.2 GB | Too big | Get file → | |
| F16 | 29.5 GB | 31.7 GB | Too big | Get file → |
For 8 GB VRAM use Q5_K_M (10.51 GB file, ~12.6 GB memory at 8k context). For 12 GB VRAM use Q6_K (12.12 GB file, ~14.2 GB memory). For higher quality with 16 GB VRAM use F16 (29.55 GB file, ~31.7 GB memory). Memory estimates are approximate.
What GPU do you need for Confucius4 T3PO?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.2 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (29.5 GB file, about 31.7 GB in use).
Which Confucius4 T3PO quant should you choose?
Q6_K (12.1 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q5_K_M at 10.5 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Confucius4 T3PO
How much VRAM does Confucius4 T3PO need?
About 14.2 GB at Q6_K with an 8K context window. That is the 12.1 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 T3PO on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Confucius4 T3PO GGUF?
It depends on the quant: Q5_K_M is 10.5 GB, Q6_K is 12.1 GB, F16 is 29.5 GB.
What context length does Confucius4 T3PO support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download Confucius4 T3PO GGUF?
The files are on Hugging Face in the netease-youdao/Confucius4-T3PO-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 T3PO use?
Hugging Face lists the license as apache-2.0. 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 T3PO on 8 GB VRAM?
Use the Q5_K_M quant. It requires about 12.6 GB of VRAM at 8k context, so 8 GB is insufficient. A lower‑bit quant is needed.
Does the model support speech input?
No. It is a text‑to‑text model. Speech can be processed with an external ASR model.
What license applies to the model?
The model is released under the Apache‑2.0 license.