Tool tree
Compare LLM inference engines on Apple Silicon. Measure tok/s, TTFT, GPU power and thermal across 10 engines. Open source CLI.
Implementation
gradeNot graded
gradeNot graded
page: Every page
query_asiai_leaderboardAnswer
Query the asiai community benchmark leaderboard for Apple Silicon LLM inference. Returns aggregated tok/s, TTFT, VRAM and sample counts grouped by hardware chip + model + engine. Optional filters: chip (e.g. "Apple M4 Pro") and model (substring match).
View tool JSON
{
"name": "query_asiai_leaderboard",
"kind": "answer",
"impl": "imperative",
"description": "Query the asiai community benchmark leaderboard for Apple Silicon LLM inference. Returns aggregated tok/s, TTFT, VRAM and sample counts grouped by hardware chip + model + engine. Optional filters: chip (e.g. \"Apple M4 Pro\") and model (substring match).",
"inputSchema": {
"type": "object",
"properties": {
"chip": {
"type": "string",
"description": "Apple Silicon chip name, e.g. \"Apple M4 Pro\", \"Apple M5 Max\"."
},
"model": {
"type": "string",
"description": "Model name or substring, e.g. \"qwen3.6\", \"gemma4:31b\"."
}
}
},
"page": "/"
}