10 actions in 9 pieces of software · ranked by words, meaning and measured trust · 673 ms
modelrecord33 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord6,649 downloads/month
- text-to-image
Task: text-to-image
- text-to-image
modelrecord
- black-forest-labs/flux-2-klein-9b-base-lora
A version of FLUX.2 [klein] 9B-base that supports fast fine-tuned lora inference
- black-forest-labs/flux-2-klein-9b-base-lora
modelrecord12,216 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- google-deepmind/gemma2-9b-it
Google's Gemma2 9b instruct model
- google-deepmind/gemma2-9b-it
modelrecord403,449 downloads/month
- text-classification
Task: text-classification
- text-classification
MCP serverrecord
- sieve_9b_decisions_decide
Answer typed questions about a state with calibrated per-option probabilities (Sieve-9B). Returns: An HTML visualization and the raw answers dict.
- sieve_9b_decisions_decide
MCP serverrecord
- lumma_fev_9b_decide
Score a document against typed questions with Lumma-Fev-9B. Returns: Rendered probability cards for every question.
- lumma_fev_9b_decide
MCP serverrecord
- lensvlm_9b_demo_preview_1
Render the document into compressed pages without running the model.
- lensvlm_9b_demo_preview
Render the document into compressed pages without running the model.
- lensvlm_9b_demo_preview_1
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.