10 actions in 9 pieces of software · ranked by words, meaning and measured trust · 584 ms
- 1GLM-4-Voice of Reason (STITCH) 9Bdemo or tutorialno passport yet
MCP serverrecord
- glm_4_voice_of_reason_stitch_9b_answer
Answer a spoken question with GLM-4-Voice of Reason (STITCH): the model thinks in silent reasoning chunks interleaved with the spoken answer, and replies with speech. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create
- glm_4_voice_of_reason_stitch_9b_answer
modelrecord
- cuuupid/glm-4v-9b
GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.
- cuuupid/glm-4v-9b
modelrecord120,339 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord11,870 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord
- google-deepmind/gemma2-9b-it
Google's Gemma2 9b instruct model
- google-deepmind/gemma2-9b-it
modelrecord
- lucataco/glm-ocr
Compact 0.9B multimodal OCR model from Z.ai. State-of-the-art on OmniDocBench V1.5 (94.62, #1 overall). Four modes: text recognition, formula (LaTeX), table parsing, and JSON-schema information extraction. Fits on a single T4.
- lucataco/glm-ocr
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
- jeeves_9b_decide
Answer yes/no, multiple-choice and rating questions about a state with Jeeves-9B. Returns: An HTML rendering of the answers and the raw Jev-format JSON response (with reasoning).
- jeeves_9b_decide
MCP serverrecord
- glm47_mcp_explain_code
Explain what a piece of code does in plain language using GLM-4.7. Returns: A clear explanation of what the code does.
- glm47_mcp_solve_problem
Solve a coding or reasoning problem step by step using GLM-4.7. Returns: A step-by-step solution with explanation and code.
- glm47_mcp_explain_code
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.