{ "host": "pve197", "gpu": "Tesla V100-PCIE-32GB", "vram_gb": 32, "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": 112.5, "prefill_tok_per_s": 240.05, "output_tokens": 256, "eval_ms": 30919.5, "decode_tok_per_s": 8.28, "load_ms": 531.1, "total_ms": 31828.4, "harness_wall_s": 31.832, "done_reason": "length" }, { "prompt_tokens": 27, "prompt_eval_ms": 113.6, "prefill_tok_per_s": 237.6, "output_tokens": 256, "eval_ms": 30399.9, "decode_tok_per_s": 8.42, "load_ms": 479.4, "total_ms": 31242.1, "harness_wall_s": 31.246, "done_reason": "length" }, { "prompt_tokens": 27, "prompt_eval_ms": 111.0, "prefill_tok_per_s": 243.16, "output_tokens": 256, "eval_ms": 30712.9, "decode_tok_per_s": 8.34, "load_ms": 483.2, "total_ms": 31552.8, "harness_wall_s": 31.557, "done_reason": "length" } ], "warmup": { "prompt_tokens": 27, "prompt_eval_ms": 843.7, "prefill_tok_per_s": 32.0, "output_tokens": 256, "eval_ms": 30499.4, "decode_tok_per_s": 8.39, "load_ms": 5877.7, "total_ms": 37664.4, "harness_wall_s": 37.668, "done_reason": "length" }, "summary": { "prefill_tok_per_s": { "min": 237.6, "median": 240.05, "max": 243.16, "n": 3 }, "decode_tok_per_s": { "min": 8.28, "median": 8.34, "max": 8.42, "n": 3 }, "total_ms": { "min": 31242.1, "median": 31552.8, "max": 31828.4, "n": 3 } } }