# Low-parameter efficiency

Granite Speech 3.3 8b
Apache-2.0
A compact and efficient speech-language model designed for Automatic Speech Recognition (ASR) and Automatic Speech Translation (AST), featuring a two-stage design for processing audio and text
Text-to-Audio Transformers English
G
ibm-granite
5,532
35
Colqwenstella 2b Multilingual
MIT
A multilingual visual retriever combining Qwen2 vision model with stella_en_1.5B_v5, ranked first among models with ≤2B parameters in Vidore benchmark
Text-to-Image Supports Multiple Languages
C
Metric-AI
175
7
TIGER DnR
Apache-2.0
TIGER is a lightweight speech separation model that achieves efficient audio processing through frequency band segmentation and multi-scale feature extraction
Sound Separation English
T
JusperLee
134
4
Conversation Summarizer V2
MIT
A fine-tuned Llama 3.2 (3B) model specialized in generating concise summaries of conversations.
Text Generation English
C
dkp2701
17
1
Bert Medium Amharic
A pre-trained Amharic language model based on the bert-medium architecture, with 40.5 million parameters trained on 290 million tokens, achieving performance comparable to larger multilingual models.
Large Language Model Transformers Other
B
rasyosef
2,661
1
Tinyllama 42M Fp32
MIT
This is a 42M-parameter Llama 2 architecture float32 precision model trained on the TinyStories dataset, suitable for simple text generation tasks.
Large Language Model Transformers
T
nickypro
517
3
Tinyllama 15M
MIT
A 15-million-parameter Llama 2 architecture model trained on the TinyStories dataset
Large Language Model Transformers
T
nickypro
3,217
11
Fairseq Dense 125M
This is a Hugging Face transformers-compatible version conversion of the 125M parameter dense model from Artetxe et al.'s paper
Large Language Model Transformers English
F
KoboldAI
27
3
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase