Google makes Gemma 3 270M IT, an open-weight, instruction-tuned chat model. It takes text input and generates text output, and is designed for tasks like question answering and summarization.
Input
Output
Context
33K
Max Output
33K
Parameters
268.1M
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 | 0.50 GB | 3.13 GB | 1x NVIDIA T4 (16 GB) |
| INT8 | 0.25 GB | 2.86 GB | 1x NVIDIA T4 (16 GB) |
| INT4 | 0.12 GB | 2.73 GB | 1x NVIDIA T4 (16 GB) |
Computed by Inferbase from the 268,098,176 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.
Specification sources
As of Nov 14, 2026.
Answered from the facts on this page, with their sources.
Gemma 3 270M IT has a context window of 32,768 tokens and a maximum output of 32,768 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Gemma 3 270M IT is an open-weight model under the Gemma license. You can download and self-host it within the license terms.
Gemma 3 270M IT has 268,098,176 parameters (268.1M), as stated in the creator's Hugging Face repository.
Gemma 3 270M IT accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for Gemma 3 270M IT yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Gemma 3 270M IT, and Inferbase runs it on your account with the same routing and logs.
The weights take 0.5 GB at FP16 / BF16, 0.2 GB at INT8, 0.1 GB at INT4, computed from the 268,098,176 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.
Start on the free plan with 5,000 requests a month, no card required.