CO

Confucius4

ConfuciusGGUF by netease-youdaoUpdated 2026-05-27
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant19.2 GB
Quick answer

Confucius4 needs about 24.7 GB of memory at Q6_K (a 22.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 19.2 GB (Q5_K_M) to 53.8 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Confucius4 – a multimodal Qwen3.5‑based LLM for reasoning and vision

Confucius4 is an open‑source multimodal LLM built on the Qwen3.5 architecture. It supports text‑only and image+text inputs with chain‑of‑thought reasoning. The model is licensed under Apache 2.0.

Good at

  • Advanced mathematical reasoning
  • Chain‑of‑thought reasoning
  • Vision‑enabled text generation

Limits

  • No vision support in the base GGUF file
  • Large memory requirement for 8k context
  • Requires llama.cpp for multimodal use

Best for

  • Mathematical problem solving
  • Multimodal content creation
  • Research prototyping

Who it’s for. Developers and researchers needing an open‑source multimodal LLM with strong reasoning capabilities. The model is suitable for projects that can run llama.cpp and handle the memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →
—53.8 GB (11 parts) 56.5 GB
Too big Get file →

For 8 GB VRAM use the Q5_K_M variant (file size 19.23 GB, estimated 21.9 GB memory). For 12 GB VRAM use Q6_K (22.08 GB, 24.7 GB memory). The unknown quant is large (53.81 GB, 56.5 GB memory) and not recommended for limited hardware.

What GPU do you need for Confucius4?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.1 GB file, about 24.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (22.1 GB file, about 24.7 GB in use).

Which Confucius4 quant should you choose?

Q6_K (22.1 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 19.2 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

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bynetease-youdao
FamilyConfucius
Licenseapache-2.0
Downloads (HF)619
Last updated2026-05-27

Frequently asked questions about Confucius4

How much VRAM does Confucius4 need?

About 24.7 GB at Q6_K with an 8K context window. That is the 22.1 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Confucius4 GGUF?

It depends on the quant: Q5_K_M is 19.2 GB, Q6_K is 22.1 GB, file is 53.8 GB.

What context length does Confucius4 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Confucius4 GGUF?

The files are on Hugging Face in the netease-youdao/Confucius4_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 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 on 8 GB VRAM?

Use the Q5_K_M quantization; it requires about 21.9 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does Confucius4 support image inputs?

Yes, it is multimodal and supports image+text inputs via llama.cpp.

Similar models

Browse all →

More from netease-youdao

All by netease-youdao →

More Confucius models

All Confucius →

Other medium models

All medium models →