{"data":{"id":"zhipu-glm-5-1-nvfp4-mtp","name":"glm-5-1-nvfp4-mtp","display_name":"GLM-5.1 NVFP4 MTP","description":"A GLM-5.1 LLM variant quantized to NVIDIA FP4 precision with multi-token prediction, enabling highly efficient GPU inference throughput.","creator":"zhipu","family":"glm","tier":"","version":"5-1","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":202752,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["tensormesh/lukealonso/GLM-5.1-NVFP4-MTP","zhipu-glm-5-1-nvfp4-mtp"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-23 08:02:26"},"meta":{"updated_at":"2026-06-23","request_id":"daea23cf-1c7d-4a9a-b137-da3d3182313e","execution_ms":1}}