Model Profiles

Profiles are ordered as endpoint name → runtime type → profile name. Each profile is bound to one exact endpoint/runtime pair.

Binding: GB10_1_openai (openai_compatible) gb10_1_openai_openai_compatible_deepseek_v4_1_flash_1017_keys · record 1ca15124d6
Use Refresh Models From Endpoints to query /v1/models. Discovery is scoped to the exact endpoint name/runtime pair.

Saved Model Records

This list is read directly from /persist/config/model_profiles.json. endpoints.json is never a model-profile source. Routing and /v1/models read this same file authority.

StatusEndpoint / profileDisplay nameUpstreamRecordActions
PUBLISHED / routable5090 (lm_studio) nvidia_5090___qwen3.5-9b-uncensored-hauhaucs-aggressiveqwen3.5-9b-uncensored-hauhaucs-aggressive via NVIDIA 5090 qwen3.5-9b-uncensored-hauhaucs-aggressivelegacy_21e
PUBLISHED / routablegb10_1 (vllm) gb10_1_vllm_qwen3_8_flash_nextqwen3.8-flash-nextqwen3.8-flash-nextlegacy_21d
PUBLISHED / routableGB10_1_openai (openai_compatible) gb10_1_openai_openai_compatible_deepseek_v4_1_flash_1017deepseek-v4.1-flash-1017deepseek-v4.1-flash-1017ee2c5b75eb
PUBLISHED / routableGB10_1_openai (openai_compatible) gb10_1_openai_openai_compatible_deepseek_v4_1_flash_1017_keysgb10_1_openai_openai_compatible_deepseek_v4_1_flash_1017_keysdeepseek-v4.1-flash-1017-keys1ca15124d6
PUBLISHED / routableGB10_1_openai (openai_compatible) gb10_1_openai_openai_compatible_glm_5_3_flash_nvfp4_abliteratedglm-5.3-flash-nvfp4-abliteratedglm-5.3-flash-nvfp4-abliterated0672965ed9

Current Model Catalog

Ordered by endpoint name, runtime type, then profile name.

Endpoint / profileDisplay nameUpstream modelOnlineDiscoveredPresetBenchmarkMetadata
5090 (lm_studio) nvidia_5090___qwen3.5-9b-uncensored-hauhaucs-aggressiveqwen3.5-9b-uncensored-hauhaucs-aggressive via NVIDIA 5090 qwen3.5-9b-uncensored-hauhaucs-aggressiveFalseFalsecreative_brainstorming— tok/s
TTFT — ms
total / active B; ; ctx
gb10_1 (vllm) gb10_1_vllm_qwen3_8_flash_nextqwen3.8-flash-nextqwen3.8-flash-nextTrueFalseglm_5_3_flash_speculative45.3 tok/s
TTFT 175 ms
6 total / 200 active B; NVFP4; 240000 ctx
GB10_1_openai (openai_compatible) gb10_1_openai_openai_compatible_deepseek_v4_1_flash_1017deepseek-v4.1-flash-1017deepseek-v4.1-flash-1017TrueFalsegeneral_assistant62.5 tok/s
TTFT 234 ms
total / active B; ; 1000000 ctx
GB10_1_openai (openai_compatible) gb10_1_openai_openai_compatible_deepseek_v4_1_flash_1017_keysgb10_1_openai_openai_compatible_deepseek_v4_1_flash_1017_keysdeepseek-v4.1-flash-1017-keysTrueTruetool_call_safe75.3 tok/s
TTFT 132 ms
total / active B; ; 1000000 ctx
GB10_1_openai (openai_compatible) gb10_1_openai_openai_compatible_glm_5_3_flash_nvfp4_abliteratedglm-5.3-flash-nvfp4-abliteratedglm-5.3-flash-nvfp4-abliteratedTrueFalseglm_5_3_flash_speculative27.8 tok/s
TTFT 274 ms
total / active B; ; ctx