Open-weight model
blt-1b-sft-tr-en
by Network for Intelligent Research Vietnam NIRVLab/blt-1b-sft-tr-en
blt-1b-sft-tr-en is an open-weight model from Network for Intelligent Research Vietnam. It has 4.6B parameters and a 4,096-token context. At 16-bit it needs about 11.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve blt-1b-sft-tr-en (4.6B 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 | 9.3 GB | 11.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.6 GB | 5.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.3 GB | 2.8 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.
blt-1b-sft-tr-en on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- BltForCausalLM
- Context length (tokens)
- 4,096
- Layers
- 25
- Vocabulary size
- 260
- Model type
- blt
Identity and Version
- Repository
- NIRVLab/blt-1b-sft-tr-en
- Publisher
- Network for Intelligent Research Vietnam
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 4.6B parameters
- Languages
- blt
- Revision
- 30fccb86a559c42c47cccac92026a3e3259af5cc
- First published
- 2026-10-13
- Last updated
- 2026-10-14
Files and Weights
7 files, 27.4 GB in total. The weights are 2 files totalling 27.4 GB in pt, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 9.3 GB | 9f6de90d25a8 |
| training_state.pt | Weights | 18.1 GB | 698e2a223bfb |
| config.json | Configuration | 3.6 KB | — |
| generation_config.json | Configuration | 91 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 6.3 KB | — |
| tokenizer_config.json | Tokenizer | 331 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 27.4 GB
Released by Network for Intelligent Research Vietnam through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 27.4 GB |
| 16-bit | 9.3 GB |
| 8-bit | 4.6 GB |
| 4-bit | 2.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About blt-1b-sft-tr-en
How much GPU memory does blt-1b-sft-tr-en need?
About 11.1 GB at 16-bit and 2.8 GB at 4-bit: the weights (4.6B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run blt-1b-sft-tr-en 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 is blt-1b-sft-tr-en's context length?
4,096 tokens, from the maximum position embeddings in its published configuration.