SAVRN
Search Contact SAVRN

Open-weight model

NextToken-model-1

by Soma Sekhar somasekhar-dev/NextToken-model-1

A 272.7M-parameter language model, pretrained from scratch on 11 Indic languages + English (Sangraha corpus), then fine-tuned on grounded multilingual QA for the Indian government-schemes / financial-banking domain (PM-KISAN, Ayushman Bharat, banking…

Parameters273M
Context2,048
Weights1.1 GB
Licenseother
AccessOpen weights
Monthly Downloads

Runs On

What it takes to serve NextToken-model-1 (273M 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 0.5 GB 0.7 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.3 GB 0.3 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.1 GB 0.2 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

A 272.7M-parameter language model, pretrained from scratch on 11 Indic languages + English (Sangraha corpus), then fine-tuned on grounded multilingual QA for the Indian government-schemes / financial-banking domain (PM-KISAN, Ayushman Bharat, banking products, insurance, savings instruments, etc.). Updated in place — this repo tracks the current best domain checkpoint, not a fixed snapshot; check back for updates as fine-tuning improves. Built from custom composable primitives, structurally equivalent to Qwen3 (confirmed by direct source comparison during HF conversion) and saved in that format for standard transformers loading: tokens/phase across H100 and V100 GPUs (best validation loss…

Excerpt from the card by Soma Sekhar, licensed other.

Configuration

Architecture
Qwen3ForCausalLM
Context length (tokens)
2,048
Layers
16
Hidden size
1,024
Feed-forward size
3,277
Attention heads
16
Key/value heads
4
Head dimension
64
Vocabulary size
68,096
Model type
qwen3

Identity and Version

Repository
somasekhar-dev/NextToken-model-1
Publisher
Soma Sekhar
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
273M parameters
Languages
Not stated by the source
Revision
5c8f2b2db5582697c15abb999edb6258c64a8254
First published
2026-09-17
Last updated
2026-09-18

Files and Weights

8 files, 1.1 GB in total. The weights are 1 file totalling 1.1 GB in safetensors.

Weights1 file · 1.1 GB
Configuration2 files · 1.4 KB
Tokenizer2 files · 8.5 MB
Documentation1 file · 4.2 KB
Other1 file · 945 B
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights1.1 GB 3f389de81218
config.jsonConfiguration1.2 KB
generation_config.jsonConfiguration195 B
README.mdDocumentation4.2 KB
chat_template.jinjaOther945 B
.gitattributesRepository1.5 KB
tokenizer.jsonTokenizer8.5 MB
tokenizer_config.jsonTokenizer440 B

License and Download

License
other
Access
Open weights, no gate
Download size
1.1 GB
Download from Soma Sekhar

Released by Soma Sekhar through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published1.1 GB
16-bit0.5 GB
8-bit0.3 GB
4-bit0.1 GB

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

Questions About NextToken-model-1

How much GPU memory does NextToken-model-1 need?

About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (273M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run NextToken-model-1 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.

What license is NextToken-model-1 released under?

other, as its publisher declares it. Read the license text before commercial use.

What is NextToken-model-1's context length?

2,048 tokens, from the maximum position embeddings in its published configuration.