{ "host": "steel141", "gpu": "RTX 3090 Ti", "vram_gb": 24, "model_alias": "gemma4:31b", "model_tag": "gemma4:31b-it-q4_K_M", "prompt_key": "long", "prompt_chars": 1614, "num_predict": 256, "num_ctx": 4096, "runs": [ { "prompt_tokens": 318, "prompt_eval_ms": 38.2, "prefill_tok_per_s": 8318.85, "output_tokens": 256, "eval_ms": 9390.5, "decode_tok_per_s": 27.26, "load_ms": 317.4, "total_ms": 9886.3, "harness_wall_s": 9.89, "done_reason": "length" }, { "prompt_tokens": 318, "prompt_eval_ms": 42.7, "prefill_tok_per_s": 7454.7, "output_tokens": 256, "eval_ms": 9429.0, "decode_tok_per_s": 27.15, "load_ms": 316.0, "total_ms": 9929.8, "harness_wall_s": 9.933, "done_reason": "length" }, { "prompt_tokens": 318, "prompt_eval_ms": 41.2, "prefill_tok_per_s": 7716.07, "output_tokens": 256, "eval_ms": 9477.4, "decode_tok_per_s": 27.01, "load_ms": 334.3, "total_ms": 9996.2, "harness_wall_s": 10.0, "done_reason": "length" } ], "warmup": { "prompt_tokens": 318, "prompt_eval_ms": 967.7, "prefill_tok_per_s": 328.62, "output_tokens": 256, "eval_ms": 9339.6, "decode_tok_per_s": 27.41, "load_ms": 324.2, "total_ms": 10774.3, "harness_wall_s": 10.778, "done_reason": "length" }, "summary": { "prefill_tok_per_s": { "min": 7454.7, "median": 7716.07, "max": 8318.85, "n": 3 }, "decode_tok_per_s": { "min": 27.01, "median": 27.15, "max": 27.26, "n": 3 }, "total_ms": { "min": 9886.3, "median": 9929.8, "max": 9996.2, "n": 3 } } }