10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 594 ms
modelrecord38,839 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord10,919 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
MCP serverrecord
- Olmo_3_32B_Base_generate
Continue a raw text prompt with the Olmo 3 32B base model (no chat template). The prompt is tokenized exactly as given (no BOS, no system prompt, no chat formatting) and the model's continuation is streamed back. Returns: The generated continuation (prompt excluded), a stats line, and the seed used.
- Olmo_3_32B_Base_generate
modelrecord
- h100-80gb-hbm3
Task: H100 80GB HBM3
- h100-80gb-hbm3
modelrecord
- lucataco/ssd-1b-img2img
Segmind Stable Diffusion Model (SSD-1B) img2img
- lucataco/ssd-1b-img2img
modelrecord
- lucataco/lcm-ssd-1b
Latent Consistency Model (LCM): SSD-1B, is a LCM distilled version that reduces the number of inference steps needed to only 2 - 8 steps
- lucataco/lcm-ssd-1b
modelrecord
- justmalhar/meta-llama-3.2-1b
Meta Llama 3.2 1B
- justmalhar/meta-llama-3.2-1b
modelrecord
- lucataco/olmocr-7b
A release preview of the olmOCR model from Ai2 that's fine tuned from Qwen2-VL-7B-Instruct using the olmOCR-mix-0225 dataset
- lucataco/olmocr-7b
- 9HobbyLM-1B Instructdemo or tutorialno passport yet
MCP serverrecord
- harims95_hobbylm_1b_instruct_respond
Chat with HobbyLM-1B Instruct. Streams the model's greedy (deterministic) answer to your message. The whole conversation so far is re-rendered with the model's chat template on every turn, so multi-turn context is kept up to the 3840-token prompt budget — longer conversations are rejected with a not
- harims95_hobbylm_1b_instruct_respond
- 10Qwen3 VL HF Demodemo or tutorialno passport yet
MCP serverrecord
- Qwen3_VL_HF_Demo_noop_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.