Qwen makes Qwen 2.5 Omni 3B, an open-source multimodal chat model. It accepts text, image, and audio inputs to generate text, image, and audio outputs.
Input
Output
Context
33K
Max Output
8K
Parameters
5.5B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 10.3 GB | 14.2 GB | 1x NVIDIA GeForce RTX 3090 (24 GB) |
| INT8 | 5.16 GB | 8.78 GB | 1x NVIDIA T4 (16 GB) |
| INT4 | 2.58 GB | 6.07 GB | 1x NVIDIA T4 (16 GB) |
Computed by Inferbase from the 5,537,120,672 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Public resources
Specification sources
As of Nov 10, 2026.
Answered from the facts on this page, with their sources.
Qwen 2.5 Omni 3B has a context window of 32,768 tokens and a maximum output of 8,000 tokens (source: Web research). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Qwen 2.5 Omni 3B is an open-weight model under the Other license. You can download and self-host it within the license terms.
Qwen 2.5 Omni 3B has 5,537,120,672 parameters (5.5B), as stated in the creator's Hugging Face repository.
Qwen 2.5 Omni 3B accepts Text, Image and Audio and produces Text, Image and Audio. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for Qwen 2.5 Omni 3B yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Qwen 2.5 Omni 3B, and Inferbase runs it on your account with the same routing and logs.
The weights take 10.3 GB at FP16 / BF16, 5.2 GB at INT8, 2.6 GB at INT4, computed from the 5,537,120,672 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
The model card of Qwen 2.5 Omni 3B lists one language: English. That is what Qwen states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.