{ "host": "steel141", "gpu": "RTX 3090 Ti", "vram_gb": 24, "model_alias": "gemma4:31b", "model_tag": "gemma4:31b-it-q4_K_M", "prompt_key": "short", "prompt_chars": 78, "num_predict": 256, "num_ctx": 4096, "runs": [ { "prompt_tokens": 27, "prompt_eval_ms": 44.1, "prefill_tok_per_s": 611.75, "output_tokens": 256, "eval_ms": 9189.5, "decode_tok_per_s": 27.86, "load_ms": 373.7, "total_ms": 9759.8, "harness_wall_s": 9.762, "done_reason": "length" }, { "prompt_tokens": 27, "prompt_eval_ms": 40.4, "prefill_tok_per_s": 668.59, "output_tokens": 256, "eval_ms": 9115.3, "decode_tok_per_s": 28.08, "load_ms": 340.5, "total_ms": 9635.7, "harness_wall_s": 9.638, "done_reason": "length" }, { "prompt_tokens": 27, "prompt_eval_ms": 40.9, "prefill_tok_per_s": 660.95, "output_tokens": 256, "eval_ms": 9123.7, "decode_tok_per_s": 28.06, "load_ms": 325.8, "total_ms": 9626.6, "harness_wall_s": 9.629, "done_reason": "length" } ], "warmup": { "prompt_tokens": 27, "prompt_eval_ms": 139.6, "prefill_tok_per_s": 193.44, "output_tokens": 256, "eval_ms": 9190.0, "decode_tok_per_s": 27.86, "load_ms": 13817.9, "total_ms": 23488.4, "harness_wall_s": 23.491, "done_reason": "length" }, "summary": { "prefill_tok_per_s": { "min": 611.75, "median": 660.95, "max": 668.59, "n": 3 }, "decode_tok_per_s": { "min": 27.86, "median": 28.06, "max": 28.08, "n": 3 }, "total_ms": { "min": 9626.6, "median": 9635.7, "max": 9759.8, "n": 3 } } }