SAVRN
Search Contact SAVRN

Open-weight model

flan-t5-xl

by Google google/flan-t5-xl

alt="drawing" width="600"/> If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages.

Parameters2.8B
Context
Weights45.6 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads186.5k

Runs On

What it takes to serve flan-t5-xl (2.8B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 5.7 GB 6.8 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 2.8 GB 3.4 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 1.4 GB 1.7 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

Model Card

By Google, published under apache-2.0, revision 7d6315df2c2f.

Model Card for FLAN-T5 XL

Table of Contents

  1. TL;DR
  2. Model Details
  3. Usage
  4. Uses
  5. Bias, Risks, and Limitations
  6. Training Details
  7. Evaluation
  8. Environmental Impact
  9. Citation

TL;DR

If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages. As mentioned in the first few lines of the abstract :

Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints,1 which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.

Disclaimer: Content from this model card has been written by the Hugging Face team, and parts of it were copy pasted from the T5 model card.

Model Details

Model Description

Read the full model card (984 words)

Configuration

Architecture
T5ForConditionalGeneration
Vocabulary size
32,128
Stored precision
float32
Model type
t5

Identity and Version

Repository
google/flan-t5-xl
Publisher
Google
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
2.8B parameters
Languages
en, fr, ro, de
Revision
7d6315df2c2fb742f0f5b556879d730926ca9001
First published
2022-10-21
Last updated
2023-11-28

Files and Weights

20 files, 45.6 GB in total. The weights are 8 files totalling 45.6 GB in bin, h5, msgpack, safetensors.

Weights8 files · 45.6 GB
Configuration7 files · 227.3 KB
Tokenizer3 files · 3.2 MB
Documentation1 file · 10.7 KB
Repository1 file · 1.4 KB
Every file
FileTypeSizeSHA-256
flax_model-00001-of-00002.msgpackWeights10.0 GB 32309ed3c4c2
flax_model-00002-of-00002.msgpackWeights1.4 GB e4ab8e7cf823
model-00001-of-00002.safetensorsWeights9.4 GB 99196ddfbe88
model-00002-of-00002.safetensorsWeights1.9 GB c0c677ddeb21
pytorch_model-00001-of-00002.binWeights9.4 GB c43a96461e48
pytorch_model-00002-of-00002.binWeights1.9 GB 60d971db8f7f
tf_model-00001-of-00002.h5Weights10.0 GB 22e2ed0ca1e1
tf_model-00002-of-00002.h5Weights1.4 GB 62647226929a
config.jsonConfiguration1.4 KB
flax_model.msgpack.index.jsonConfiguration51.2 KB
generation_config.jsonConfiguration147 B
model.safetensors.index.jsonConfiguration53.0 KB
pytorch_model.bin.index.jsonConfiguration50.8 KB
special_tokens_map.jsonConfiguration2.2 KB
tf_model.h5.index.jsonConfiguration68.5 KB
README.mdDocumentation10.7 KB
.gitattributesRepository1.4 KB
spiece.modelTokenizer791.7 KB d60acb128cf7
tokenizer.jsonTokenizer2.4 MB
tokenizer_config.jsonTokenizer2.5 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
45.6 GB
Download from Google

Released by Google through Kaggle. Read the license.

Built From

  • Described by arXiv:1910.09700
  • Described by arXiv:2210.11416
  • Trained on (disclosed) aqua_rat
  • Trained on (disclosed) deepmind/code_contests
  • Trained on (disclosed) djaym7/wiki_dialog
  • Trained on (disclosed) esnli
  • Trained on (disclosed) gsm8k
  • Trained on (disclosed) lambada
  • Trained on (disclosed) qed
  • Trained on (disclosed) quasc
  • Trained on (disclosed) svakulenk0/qrecc
  • Trained on (disclosed) taskmaster2

Memory Requirements

PrecisionWeights in memory
As published45.6 GB
16-bit5.7 GB
8-bit2.8 GB
4-bit1.4 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About flan-t5-xl

How much GPU memory does flan-t5-xl need?

About 6.8 GB at 16-bit and 1.7 GB at 4-bit: the weights (2.8B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run flan-t5-xl on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use flan-t5-xl commercially?

Yes. flan-t5-xl is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.