Google's Flan T5 Small is an open-source language model designed for text-to-text tasks. It is a chat model that takes text inputs and returns text outputs, capable of calling tools for extended thinking and streaming responses.
Input
Output
Context
512
Max Output
128
Parameters
77M
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
Download 0.31 GB · 15 GGUF builds
| Precision | Weights | One request at 512 tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 0.14 GB | 0.19 GB | 1x NVIDIA A100 SXM 40GB (40 GB) |
| INT8 | 0.07 GB | 0.12 GB | 1x NVIDIA GeForce RTX 3090 (24 GB) |
| INT4 | 0.04 GB | 0.08 GB | 1x NVIDIA T4 (16 GB) |
Computed by Inferbase from the 76,961,152 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 11, 2026.
Answered from the facts on this page, with their sources.
Flan T5 Small has a context window of 512 tokens and a maximum output of 128 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Flan T5 Small is an open-weight model under the Apache 2.0 license. You can download and self-host it within the license terms.
Flan T5 Small has 76,961,152 parameters (77M), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (apache-2.0). Limitations: Short context window: 512 tokens. Each is computed from the model's stated facts and benchmark results.
Flan T5 Small 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 Flan T5 Small yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Flan T5 Small, and Inferbase runs it on your account with the same routing and logs.
The weights take 0.1 GB at FP16 / BF16, 0.1 GB at INT8, 0.0 GB at INT4, computed from the 76,961,152 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 Flan T5 Small lists 4 languages: English, French, Romanian and German. That is what Google states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.