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…
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.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also 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.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.1 GB | 3f389de81218 |
| config.json | Configuration | 1.2 KB | — |
| generation_config.json | Configuration | 195 B | — |
| README.md | Documentation | 4.2 KB | — |
| chat_template.jinja | Other | 945 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 8.5 MB | — |
| tokenizer_config.json | Tokenizer | 440 B | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 1.1 GB
Released by Soma Sekhar through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.1 GB |
| 16-bit | 0.5 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.1 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.