t5-title-model is an open-weight model from Bay. It has 61M parameters. At 16-bit it needs about 0.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 30 downloads a month.
Small T5 (google/t5-efficient-small) trained from scratch for chat sidebar title Prompt format is exactly User: {message}\nTitle: (note the trailing space). Beam search (numbeams=4) is what the eval used.
Runs On
What it takes to serve t5-title-model (61M 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 | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 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 Oct 18, 2026.
t5-title-model on every accelerator the SAVRN Index prices, at every precision
Model Card
Small T5 (google/t5-efficient-small) trained from scratch for chat sidebar title Prompt format is exactly User: {message}\nTitle: (note the trailing space). Beam search (numbeams=4) is what the eval used. An int4 export lives in the int4/ subfolder (see below). The root repo is the fp16 model. The residual stream of this checkpoint reaches ~82k at the last encoder block, which overflows fp16 max (65504) and produces nan. Train/eval it in bf16, never fp16. fp32 also works. The stored weights are fp16/bfloat16-compatible safetensors. - 2 epochs, 2xT4, bf16, batch 16 x grad-accum 4 - best evalloss 2.7184 (Trainer-reported; inflated ~1.79x by grad-accum reporting, true eval loss ~1.52) Measured…
Excerpt from the card by Bay.
Configuration
- Architecture
- T5ForConditionalGeneration
- Vocabulary size
- 32,128
- Model type
- t5
Identity and Version
- Repository
- baylikestempura/t5-title-model
- Publisher
- Bay
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 61M parameters
- Languages
- Not stated by the source
- Revision
- 7a9d319eacae6cb5ca316d9c6fae120acc166697
- First published
- 2026-09-30
- Last updated
- 2026-10-10
Files and Weights
15 files, 489.4 MB in total. The weights are 4 files totalling 485.2 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| int4/dequant/model.safetensors | Weights | 219.7 MB | dca72e6a2969 |
| int4/int4_scales.safetensors | Weights | 1.4 MB | 0b1bae4e8b40 |
| int4/int4_weights.safetensors | Weights | 22.0 MB | d05cc74b289f |
| model.safetensors | Weights | 242.0 MB | 3ef62ffeaaea |
| config.json | Configuration | 786 B | — |
| generation_config.json | Configuration | 151 B | — |
| int4/config.json | Configuration | 787 B | — |
| int4/manifest.json | Configuration | 14.5 KB | — |
| int4/qat_report.json | Configuration | 181 B | — |
| README.md | Documentation | 3.8 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| int4/tokenizer.json | Tokenizer | 2.1 MB | — |
| int4/tokenizer_config.json | Tokenizer | 2.5 KB | — |
| tokenizer.json | Tokenizer | 2.1 MB | — |
| tokenizer_config.json | Tokenizer | 2.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 485.2 MB
Released by Bay through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 485.2 MB |
| 16-bit | 0.1 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About t5-title-model
How much GPU memory does t5-title-model need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (61M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run t5-title-model 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.