Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text generation

BAAR8-44M-Vision

by BAAR aixk/BAAR8-44M-Vision

BAAR8-44M-Vision is an open-weight model for text generation from BAAR, released under other. It has 44M parameters and a 512-token context. 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.

BAAR8-45M-Vision is an ultra-compact multilingual conversational model designed to enable real-time chat under minimal hardware conditions.

Parameters44M
Context512
Weights1.1 GB
Licenseother
AccessOpen weights
Monthly Downloads—

Runs On

What it takes to serve BAAR8-44M-Vision (44M 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 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.0 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 19, 2026.

BAAR8-44M-Vision on every accelerator the SAVRN Index prices, at every precision

Model Card

BAAR8-45M-Vision is an ultra-compact multilingual conversational model designed to enable real-time chat under minimal hardware conditions. With just 9 million (9M) parameters, it brings lightweight, interactive dialogue capabilities across 11 languages to extreme resource-constrained environments, embedded devices, and on-device platforms where standard LLMs cannot operate. BAAR8-45M-Vision은 최소한의 하드웨어 여건과 극단적인 리소스 제약 환경에서도 11개 언어로 실시간 대화(Chat)가 가능하도록 설계된 900만(9M) 파라미터 규모의 초경량 다국어 언어 모델입니다. 일반적인 대형 모델 구동이 불가능한 초저사양 엣지 및 임베디드 기기에서도 즉각적인 대화형 추론과 초경량 실시간 RAG 시스템 구축을 지원합니다. - Non-Commercial Use Only (비상업적 연구·개인 이용 한정): This model is strictly provided for non-commercial, research, and…

Excerpt from the card by BAAR, licensed other.

Configuration

Architecture
FHN_T4Max_150M_SingleHead_GAU
Context length (tokens)
512
Layers
23
Hidden size
512
Attention heads
1
Vocabulary size
3,072
Stored precision
float16
Model type
fhn_concept_gau

Identity and Version

Repository
aixk/BAAR8-44M-Vision
Publisher
BAAR
Task
Text generation
Modality
Text
Library
Not stated by the source
Parameters
44M parameters
Languages
ko, en, ja, zh, es, pt, de, ru
Revision
745b47b0566cdd0728789e339f324ba9d36df59c
First published
2026-10-11
Last updated
2026-10-12

Files and Weights

13 files, 1.2 GB in total. The weights are 3 files totalling 1.1 GB in pt, safetensors.

Weights3 files · 1.1 GB
Configuration3 files · 966 B
Tokenizer3 files · 1.1 MB
Documentation1 file · 6.4 KB
Other2 files · 72.9 MB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
checkpoint_step_17000.ptWeights516.7 MB af643c0860c6
checkpoint_step_18000.ptWeights516.7 MB fe8ac30b2935
model.safetensorsWeights87.4 MB 87224ff83415
baar3_manifest.jsonConfiguration442 B —
config.jsonConfiguration426 B —
special_tokens_map.jsonConfiguration98 B —
README.mdDocumentation6.4 KB —
model_int4_wasm.baar3Other25.6 MB 7963656bc82f
model_int8_wasm.baar3Other47.4 MB 73984e4de540
.gitattributesRepository1.6 KB —
tokenizer.jsonTokenizer59.5 KB —
tokenizer_config.jsonTokenizer146 B —
tokenizer_state.jsonTokenizer1.1 MB —

License and Download

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

Released by BAAR through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published1.1 GB
16-bit0.1 GB
8-bit0.0 GB
4-bit0.0 GB

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

Questions About BAAR8-44M-Vision

How much GPU memory does BAAR8-44M-Vision need?

About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (44M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run BAAR8-44M-Vision 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 BAAR8-44M-Vision released under?

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

What is BAAR8-44M-Vision's context length?

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

Similar Models

Model · Text generation

luna-1.5-flash

AobanZ

We introduce LUNA, a small, autoregressive transformer. This model aims to provide conversational-like chat without overloading the computer. This model is designed to run on small hardware, such as phones or office computers. Luna utilizes FlashAttention and AdamW for performance and capability. Lightning is designed to provide quick, coherent outputs, improved with a larger size and weight. Luna is intended to be used for research, analysis and fine-tuning, general conversation, stories and other. It is not intended to be used for professional advice, real writing or any kind of heavy work as generated outputs may be incorrect. Luna can be used directly for text generation…

Open weights mit 43M parameters transformers
View model