{ "host": "pve197", "gpu": "Tesla V100-PCIE-32GB", "vram_gb": 32, "model_alias": "gemma4:26b", "model_tag": "gemma4:26b", "prompt_key": "long", "prompt_chars": 1614, "num_predict": 256, "num_ctx": 4096, "runs": [ { "prompt_tokens": 318, "prompt_eval_ms": 118.0, "prefill_tok_per_s": 2695.59, "output_tokens": 256, "eval_ms": 32720.5, "decode_tok_per_s": 7.82, "load_ms": 475.8, "total_ms": 33548.1, "harness_wall_s": 33.555, "done_reason": "length" }, { "prompt_tokens": 318, "prompt_eval_ms": 118.3, "prefill_tok_per_s": 2689.01, "output_tokens": 256, "eval_ms": 31273.0, "decode_tok_per_s": 8.19, "load_ms": 492.5, "total_ms": 32116.6, "harness_wall_s": 32.123, "done_reason": "length" }, { "prompt_tokens": 318, "prompt_eval_ms": 117.3, "prefill_tok_per_s": 2711.41, "output_tokens": 256, "eval_ms": 33434.9, "decode_tok_per_s": 7.66, "load_ms": 496.0, "total_ms": 34298.7, "harness_wall_s": 34.305, "done_reason": "length" } ], "warmup": { "prompt_tokens": 318, "prompt_eval_ms": 3562.7, "prefill_tok_per_s": 89.26, "output_tokens": 256, "eval_ms": 32215.7, "decode_tok_per_s": 7.95, "load_ms": 491.7, "total_ms": 36521.3, "harness_wall_s": 36.529, "done_reason": "length" }, "summary": { "prefill_tok_per_s": { "min": 2689.01, "median": 2695.59, "max": 2711.41, "n": 3 }, "decode_tok_per_s": { "min": 7.66, "median": 7.82, "max": 8.19, "n": 3 }, "total_ms": { "min": 32116.6, "median": 33548.1, "max": 34298.7, "n": 3 } } }