tangkhul-byt5-base is an open-weight model from Chormi Zimik Vashai. It has 582M parameters. At 16-bit it needs about 1.4 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 24 downloads a month.
Runs On
What it takes to serve tangkhul-byt5-base (582M 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 | 1.2 GB | 1.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.3 GB | 0.3 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 20, 2026.
tangkhul-byt5-base on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- T5ForConditionalGeneration
- Vocabulary size
- 384
- Model type
- t5
Identity and Version
- Repository
- chormi/tangkhul-byt5-base
- Publisher
- Chormi Zimik Vashai
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 582M parameters
- Languages
- Not stated by the source
- Revision
- 247df57592383250af72e5c7be6546d5656d2707
- First published
- 2026-09-19
- Last updated
- 2026-09-20
Files and Weights
6 files, 2.3 GB in total. The weights are 1 file totalling 2.3 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 2.3 GB | 82739b7a6211 |
| added_tokens.json | Configuration | 3.0 KB | — |
| config.json | Configuration | 871 B | — |
| generation_config.json | Configuration | 142 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer_config.json | Tokenizer | 28.3 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 2.3 GB
Released by Chormi Zimik Vashai through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.3 GB |
| 16-bit | 1.2 GB |
| 8-bit | 0.6 GB |
| 4-bit | 0.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About tangkhul-byt5-base
How much GPU memory does tangkhul-byt5-base need?
About 1.4 GB at 16-bit and 0.3 GB at 4-bit: the weights (582M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run tangkhul-byt5-base 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.