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.
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.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also 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
- TL;DR
- Model Details
- Usage
- Uses
- Bias, Risks, and Limitations
- Training Details
- Evaluation
- Environmental Impact
- 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
Configuration
- Architecture
- T5ForConditionalGeneration
- Vocabulary size
- 32,128
- Stored precision
- float32
- Model type
- t5
Identity and Version
- Repository
- google/flan-t5-xl
- Publisher
- 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.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| flax_model-00001-of-00002.msgpack | Weights | 10.0 GB | 32309ed3c4c2 |
| flax_model-00002-of-00002.msgpack | Weights | 1.4 GB | e4ab8e7cf823 |
| model-00001-of-00002.safetensors | Weights | 9.4 GB | 99196ddfbe88 |
| model-00002-of-00002.safetensors | Weights | 1.9 GB | c0c677ddeb21 |
| pytorch_model-00001-of-00002.bin | Weights | 9.4 GB | c43a96461e48 |
| pytorch_model-00002-of-00002.bin | Weights | 1.9 GB | 60d971db8f7f |
| tf_model-00001-of-00002.h5 | Weights | 10.0 GB | 22e2ed0ca1e1 |
| tf_model-00002-of-00002.h5 | Weights | 1.4 GB | 62647226929a |
| config.json | Configuration | 1.4 KB | — |
| flax_model.msgpack.index.json | Configuration | 51.2 KB | — |
| generation_config.json | Configuration | 147 B | — |
| model.safetensors.index.json | Configuration | 53.0 KB | — |
| pytorch_model.bin.index.json | Configuration | 50.8 KB | — |
| special_tokens_map.json | Configuration | 2.2 KB | — |
| tf_model.h5.index.json | Configuration | 68.5 KB | — |
| README.md | Documentation | 10.7 KB | — |
| .gitattributes | Repository | 1.4 KB | — |
| spiece.model | Tokenizer | 791.7 KB | d60acb128cf7 |
| tokenizer.json | Tokenizer | 2.4 MB | — |
| tokenizer_config.json | Tokenizer | 2.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 45.6 GB
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
| Precision | Weights in memory |
|---|---|
| As published | 45.6 GB |
| 16-bit | 5.7 GB |
| 8-bit | 2.8 GB |
| 4-bit | 1.4 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.