QW

Qwen2.5 Omni 3B

QwenGGUF by ggml-orgUpdated 2025-05-26
Download on Hugging Face
Parameters3.4B
Context32K
Layers36
Architectureqwen2vl
Smallest quant2.1 GB
Quick answer

Qwen2.5 Omni 3B needs about 2.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 2.1 GB (Q4_K_M) to 6.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

Qwen2.5 Omni 3B – a 3.4B multimodal model for text, audio, and image input

Qwen2.5 Omni 3B is a 3.4‑billion‑parameter multimodal model that accepts text, audio, and image inputs. It is quantized for use with llama.cpp and supports streaming text generation. The model is based on the Qwen2.5‑Omni architecture and was released by ggml-org.

Good at

  • Multimodal input handling
  • Text generation from audio and images
  • Streaming responses

Limits

  • No video input or audio generation
  • Requires 8‑k context for memory estimates
  • License type is other

Best for

  • Chatbots needing image and audio understanding
  • Voice‑to‑text applications
  • Multimodal content creation

Who it’s for. Developers building lightweight multimodal assistants that run on local hardware. The model is suitable for projects that need text, audio, and image processing without video or audio output capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.1 GB 2.9 GB
Fits Get file →
Q8_03.6 GB 4.4 GB
Fits Get file →
F166.8 GB 7.6 GB
Tight Get file →

For 8 GB VRAM, use the Q4_K_M quant (2.1 GB file, ~2.9 GB RAM at 8 k context). If 12 GB VRAM is available, Q8_0 (3.62 GB file, ~4.4 GB RAM) offers higher precision. The F16 quant (6.8 GB file, ~7.6 GB RAM) requires more memory and is best for systems with 16 GB+ VRAM.

What GPU do you need for Qwen2.5 Omni 3B?

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: the best quant that fits is Q4_K_M (2.1 GB file, about 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.4 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.8 GB file, about 7.6 GB in use).

Which Qwen2.5 Omni 3B quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 Omni 3B: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters3.4B
Layers36
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized byggml-org
FamilyQwen
Licenseother
Downloads (HF)85,778
Last updated2025-05-26

Frequently asked questions about Qwen2.5 Omni 3B

How much VRAM does Qwen2.5 Omni 3B need?

About 2.9 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Qwen2.5 Omni 3B on an 8 GB GPU?

Yes, with F16: the 6.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2.5 Omni 3B GGUF?

It depends on the quant: Q4_K_M is 2.1 GB, Q8_0 is 3.6 GB, F16 is 6.8 GB.

What context length does Qwen2.5 Omni 3B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download Qwen2.5 Omni 3B GGUF?

The files are on Hugging Face in the ggml-org/Qwen2.5-Omni-3B-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 Qwen2.5 Omni 3B 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 Qwen2.5 Omni 3B on 8 GB VRAM?

Yes, the Q4_K_M quant uses about 2.9 GB of VRAM at 8 k context, which fits within 8 GB.

Does the model support video input?

No, the model only accepts text, audio, and image inputs; video is not supported.

Can I generate audio with this model?

No, audio generation is not enabled in the current GGUF build.

Other GGUFs of Qwen2.5-Omni-3B

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Qwen models

All Qwen →

Other tiny models

All tiny models →