10 actions in 7 pieces of software · ranked by words, meaning and measured trust · 665 ms
modelrecord47 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord39,187 downloads/month
- automatic-speech-recognition
Task: automatic-speech-recognition
- automatic-speech-recognition
modelrecord
- riva
Task: Riva
- h100-80gb-hbm3
Task: H100 80GB HBM3
- conversational-ai
Task: Conversational AI
- speech-to-text
Task: Speech to Text
- riva
modelrecord
- nvidia/sana-sprint-1.6b
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
- nvidia/sana-sprint-1.6b
modelrecord76,305 downloads/month
- fill-mask
Task: fill-mask
- fill-mask
modelrecord
- 01-ai/yi-6b
The Yi series models are large language models trained from scratch by developers at 01.AI.
- 01-ai/yi-6b
MCP serverrecord
- lumma_0_6b_base_demo_generate
Generate text completion from a prompt using Lumma-0.6B-Base. Lumma-0.6B is a multilingual (English + 10 Indic languages) base language model with a Shared KV caching strategy that reduces KV-cache memory by ~50%.
- lumma_0_6b_base_demo_generate
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.