{ "host": "steel141", "gpu": "RTX 3090 Ti", "vram_gb": 24, "model_alias": "gemma4:26b", "model_tag": "gemma4:26b", "prompt_key": "short", "prompt_chars": 78, "num_predict": 256, "num_ctx": 4096, "runs": [ { "prompt_tokens": 27, "prompt_eval_ms": 19.8, "prefill_tok_per_s": 1366.3, "output_tokens": 256, "eval_ms": 2089.1, "decode_tok_per_s": 122.54, "load_ms": 361.8, "total_ms": 2614.4, "harness_wall_s": 2.617, "done_reason": "length" }, { "prompt_tokens": 27, "prompt_eval_ms": 12.9, "prefill_tok_per_s": 2088.79, "output_tokens": 256, "eval_ms": 1996.8, "decode_tok_per_s": 128.2, "load_ms": 341.7, "total_ms": 2489.2, "harness_wall_s": 2.491, "done_reason": "length" }, { "prompt_tokens": 27, "prompt_eval_ms": 13.1, "prefill_tok_per_s": 2062.75, "output_tokens": 256, "eval_ms": 1995.2, "decode_tok_per_s": 128.31, "load_ms": 330.7, "total_ms": 2473.9, "harness_wall_s": 2.476, "done_reason": "length" } ], "warmup": { "prompt_tokens": 27, "prompt_eval_ms": 47.7, "prefill_tok_per_s": 566.39, "output_tokens": 256, "eval_ms": 2014.5, "decode_tok_per_s": 127.08, "load_ms": 4346.8, "total_ms": 6739.3, "harness_wall_s": 6.752, "done_reason": "length" }, "summary": { "prefill_tok_per_s": { "min": 1366.3, "median": 2062.75, "max": 2088.79, "n": 3 }, "decode_tok_per_s": { "min": 122.54, "median": 128.2, "max": 128.31, "n": 3 }, "total_ms": { "min": 2473.9, "median": 2489.2, "max": 2614.4, "n": 3 } } }