Based on Qwen3.5 | License: Apache 2.0
This model was converted to GGUF format from netease-youdao/Confucius4 using llama.cpp.
Refer to the original model card for more details on the model.
Confucius4 is an open-source multimodal LLM developed by the NetEase Youdao AI Team, built upon the Qwen3.5 architecture and designed for advanced mathematical reasoning. It supports both text-only and image+text inputs with chain-of-thought reasoning.
We provide multiple quantization variants, stored in their respective subdirectories:
| Quant | Directory | Use Case |
|---|---|---|
| BF16 (F16 GGUF) | bf16/ | Reference, lossless (split into 11 shards) |
| Q6_K | Q6_K/ | Near-lossless, high quality |
| Q5_K_M | Q5_K_M/ | Recommended balanced quality/size |
Before running the model, please compile and install llama.cpp first.
Since the BF16 models we uploaded have been sliced, you need to execute the following commands to merge the models before running them.
./build/bin/llama-gguf-split --merge bf16/Confucius4-00001-of-00011.gguf Confucius4-bf16.ggufThe mmproj (vision encoder) is provided as a single file, no merge needed.
./build/bin/llama-server \
-m Q5_K_M/Confucius4-Q5_K_M.gguf \
--mmproj bf16/mmproj-Confucius4.gguf \
--port 8080 \
-c 20000 \
-ngl 99Then send requests to http://localhost:8080/v1/chat/completions.
./build/bin/llama-cli \
-m Q5_K_M/Confucius4-Q5_K_M.gguf \
-p "<|im_start|>user\nWhat is the derivative of x^2 * sin(x)?<|im_end|>\n<|im_start|>assistant\n" \
-n 2048We also provide a run_gguf_server.sh script for quick startup:
# CPU only
sh run_gguf_server.sh Q5_K_M --cpu
# GPU with default settings
sh run_gguf_server.sh Q5_K_M
# Custom port and context length
sh run_gguf_server.sh Q5_K_M -p 8080 -c 16384The model uses a simple system prompt. You can use the following template:
You are a helpful assistant.The chat format uses the Qwen3.5 template with thinking support:
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
{{QUERY}}<|im_end|>
<|im_start|>assistant
<think>
(chain-of-thought reasoning)
</think>
(final answer)
<|im_end|>Generate Parameters: We suggest using Temperature=0.6, TopP=0.95, TopK=20 to sample.
We evaluated the Q5_K_M quantized version on the Math-Figure dataset. Other quantization variants and benchmarks have not been tested — users are encouraged to explore them on their own.
| Model | Math-Figure |
|---|---|
| Confucius4 (original) | 0.907 |
| Confucius4-Q5_K_M (GGUF) | 0.895 |
Note: Only the Q5_K_M quantization has been evaluated on Math-Figure. Results for other quantization levels (BF16, Q6_K) and other benchmarks may vary.
convert_hf_to_gguf.py with --outtype f16 --no-mtp--mmproj and stored in the bf16/ folder. When launching VLM services (e.g., llama-server with image support), the mmproj file must be loaded from bf16/mmproj-Confucius4.ggufllama-quantizeSignificant thanks to the llama.cpp project for providing the GGUF conversion and inference tools. We also acknowledge the ms-swift team for the fine-tuning framework and the Qwen team for their foundational models.
This project is released under the Apache License 2.0.
If you find our work helpful, feel free to give us a cite.
@misc{confucius4,
title = {Confucius4: Advancing Multimodal Reasoning with Iterative SFT-RL Optimization and Compact Chain-of-Thought},
author = {NetEase Youdao AI Team},
year = {2026},
publisher = {Hugging Face},
howpublished = {\url{https://huggingface.co/netease-youdao/Confucius4}}
}