{"object":"list","data":[{"id":"casperhansen/mistral-nemo-instruct-2407-awq","object":"model","created":1779471253,"owned_by":"vllm","root":"casperhansen/mistral-nemo-instruct-2407-awq","parent":null,"max_model_len":10000,"permission":[{"id":"modelperm-eb124da9a9eb4384aab6ce98b689cf00","object":"model_permission","created":1779471253,"allow_create_engine":false,"allow_sampling":true,"allow_logprobs":true,"allow_search_indices":false,"allow_view":true,"allow_fine_tuning":false,"organization":"*","group":null,"is_blocking":false}],"alias":"casperhansen/mistral-nemo-instruct-2407-awq","state":"LOADED","active":true,"ttl_remaining_seconds":46800,"config":{"quantization":"awq_marlin","dtype":"auto","gpu_memory_utilization":0.85,"max_model_len":10000,"max_num_seqs":64,"max_num_batched_tokens":16384,"tensor_parallel_size":1,"ttl_seconds":46800},"vram":{"gpu_vram_used_mib":21481,"gpu_vram_total_mib":24576,"gpu_vram_free_mib":2682,"gpu_vram_utilization_pct":84,"gpu_kv_cache_utilization_pct":0.0}},{"id":"Qwen/Qwen2.5-VL-7B-Instruct","object":"model","created":1779471253,"owned_by":"vllm","root":"Qwen/Qwen2.5-VL-7B-Instruct","parent":null,"max_model_len":16384,"permission":[{"id":"modelperm-Qwen/Qwen2.5-VL-7B-Instruct","object":"model_permission","created":1779471253,"allow_create_engine":false,"allow_sampling":true,"allow_logprobs":true,"allow_search_indices":false,"allow_view":true,"allow_fine_tuning":false,"organization":"*","group":null,"is_blocking":false}],"alias":"Qwen/Qwen2.5-VL-7B-Instruct","state":"IDLE","active":false,"ttl_remaining_seconds":0,"config":{"quantization":"bitsandbytes","dtype":"bfloat16","gpu_memory_utilization":0.85,"max_model_len":16384,"max_num_seqs":4,"max_num_batched_tokens":32768,"tensor_parallel_size":1,"ttl_seconds":28800},"vram":{"gpu_vram_used_mib":null,"gpu_vram_total_mib":null,"gpu_vram_free_mib":null,"gpu_vram_utilization_pct":null,"gpu_kv_cache_utilization_pct":null}},{"id":"Qwen/Qwen2-VL-7B-Instruct","object":"model","created":1779471253,"owned_by":"vllm","root":"Qwen/Qwen2-VL-7B-Instruct","parent":null,"max_model_len":16384,"permission":[{"id":"modelperm-Qwen/Qwen2-VL-7B-Instruct","object":"model_permission","created":1779471253,"allow_create_engine":false,"allow_sampling":true,"allow_logprobs":true,"allow_search_indices":false,"allow_view":true,"allow_fine_tuning":false,"organization":"*","group":null,"is_blocking":false}],"alias":"Qwen/Qwen2-VL-7B-Instruct","state":"IDLE","active":false,"ttl_remaining_seconds":0,"config":{"quantization":"bitsandbytes","dtype":"bfloat16","gpu_memory_utilization":0.85,"max_model_len":16384,"max_num_seqs":4,"max_num_batched_tokens":32768,"tensor_parallel_size":1,"ttl_seconds":28800},"vram":{"gpu_vram_used_mib":null,"gpu_vram_total_mib":null,"gpu_vram_free_mib":null,"gpu_vram_utilization_pct":null,"gpu_kv_cache_utilization_pct":null}}]}