10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 637 ms
modelrecord45,581 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
modelrecord13,228 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord153,206 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- spuuntries/flatdolphinmaid-8x7b-gguf
Undi95's FlatDolphinMaid 8x7B Mixtral Merge, GGUF Q5_K_M quantized by TheBloke.
- spuuntries/flatdolphinmaid-8x7b-gguf
libraryggml-org/llama.cpprecord5,488,885 downloads/month
- gguf
modelrecord
- lucataco/gemma-4-31b-it
Gemma 4 31B Instruct - Google open-weight VLM (image + text in, text out)
- lucataco/gemma-4-31b-it
modelrecord
- spuuntries/miqumaid-v1-70b-gguf
NeverSleep's MiquMaid v1 70B Miqu Finetune, GGUF Q3_K_M quantized by NeverSleep.
- spuuntries/miqumaid-v1-70b-gguf
modelrecord18,800 downloads/month
- audio-to-audio
Task: audio-to-audio
- audio-to-audio
modelrecord164,842 downloads/month
- text-to-speech
Task: text-to-speech
- text-to-speech
modelrecord268,387 downloads/month
- video-to-video
Task: video-to-video
- video-to-video
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.