TowerVision Extending Tower capabilities to the vision modality utter-project/TowerVision-2B Image-Text-to-Text • 3B • Updated Nov 5, 2025 • 185 • 6 utter-project/TowerVision-9B Image-Text-to-Text • 10B • Updated Nov 5, 2025 • 135 • 4 utter-project/TowerVideo-2B Video-Text-to-Text • 3B • Updated Oct 28, 2025 • 70 • 3 utter-project/TowerVideo-9B Video-Text-to-Text • 10B • Updated Oct 28, 2025 • 61 • 5
mHuBERT-147 models Compact yet powerful multilingual speech representation models based on the HuBERT architecture. utter-project/mHuBERT-147-base-1st-iter Feature Extraction • 94.4M • Updated Jan 23, 2025 • 77 • 2 utter-project/mHuBERT-147-base-2nd-iter Feature Extraction • 94.4M • Updated Jan 23, 2025 • 1.13k • • 3 utter-project/mHuBERT-147 Feature Extraction • 94.4M • Updated Jun 1 • 33.9k • • 108
utter-project/mHuBERT-147-base-2nd-iter Feature Extraction • 94.4M • Updated Jan 23, 2025 • 1.13k • • 3
Spire Extending Tower to the speech modality. Spire models are multimodal LLMs capable of transcribing and translating English into 9 different languages. utter-project/SpireBase 7B • Updated Sep 9, 2025 • 62 • 4 utter-project/SpireFull 7B • Updated Sep 9, 2025 • 31 • 2 utter-project/SpireNoBlocks 7B • Updated Sep 9, 2025 • 36 utter-project/SpireNoPseudo 7B • Updated Sep 9, 2025 • 36
EuroLLM utter-project/EuroLLM-1.7B Text Generation • Updated Nov 27, 2024 • 10.7k • 122 utter-project/EuroLLM-9B Text Generation • 9B • Updated Dec 9, 2024 • 2.17k • 171 utter-project/EuroLLM-1.7B-Instruct Text Generation • 2B • Updated Dec 16, 2024 • 19.5k • 104 utter-project/EuroLLM-9B-Instruct Text Generation • 9B • Updated Dec 9, 2024 • 11.1k • 228
TowerVision Extending Tower capabilities to the vision modality utter-project/TowerVision-2B Image-Text-to-Text • 3B • Updated Nov 5, 2025 • 185 • 6 utter-project/TowerVision-9B Image-Text-to-Text • 10B • Updated Nov 5, 2025 • 135 • 4 utter-project/TowerVideo-2B Video-Text-to-Text • 3B • Updated Oct 28, 2025 • 70 • 3 utter-project/TowerVideo-9B Video-Text-to-Text • 10B • Updated Oct 28, 2025 • 61 • 5
Spire Extending Tower to the speech modality. Spire models are multimodal LLMs capable of transcribing and translating English into 9 different languages. utter-project/SpireBase 7B • Updated Sep 9, 2025 • 62 • 4 utter-project/SpireFull 7B • Updated Sep 9, 2025 • 31 • 2 utter-project/SpireNoBlocks 7B • Updated Sep 9, 2025 • 36 utter-project/SpireNoPseudo 7B • Updated Sep 9, 2025 • 36
mHuBERT-147 models Compact yet powerful multilingual speech representation models based on the HuBERT architecture. utter-project/mHuBERT-147-base-1st-iter Feature Extraction • 94.4M • Updated Jan 23, 2025 • 77 • 2 utter-project/mHuBERT-147-base-2nd-iter Feature Extraction • 94.4M • Updated Jan 23, 2025 • 1.13k • • 3 utter-project/mHuBERT-147 Feature Extraction • 94.4M • Updated Jun 1 • 33.9k • • 108
utter-project/mHuBERT-147-base-2nd-iter Feature Extraction • 94.4M • Updated Jan 23, 2025 • 1.13k • • 3
EuroLLM utter-project/EuroLLM-1.7B Text Generation • Updated Nov 27, 2024 • 10.7k • 122 utter-project/EuroLLM-9B Text Generation • 9B • Updated Dec 9, 2024 • 2.17k • 171 utter-project/EuroLLM-1.7B-Instruct Text Generation • 2B • Updated Dec 16, 2024 • 19.5k • 104 utter-project/EuroLLM-9B-Instruct Text Generation • 9B • Updated Dec 9, 2024 • 11.1k • 228
