{ "host": "steel141", "gpu": "RTX 3090 Ti", "vram_gb": 24, "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": 12.5, "prefill_tok_per_s": 25397.83, "output_tokens": 256, "eval_ms": 1988.3, "decode_tok_per_s": 128.76, "load_ms": 319.7, "total_ms": 2461.3, "harness_wall_s": 2.465, "done_reason": "length" }, { "prompt_tokens": 318, "prompt_eval_ms": 13.3, "prefill_tok_per_s": 23848.87, "output_tokens": 256, "eval_ms": 1999.2, "decode_tok_per_s": 128.05, "load_ms": 343.2, "total_ms": 2500.0, "harness_wall_s": 2.503, "done_reason": "length" }, { "prompt_tokens": 318, "prompt_eval_ms": 14.2, "prefill_tok_per_s": 22372.04, "output_tokens": 256, "eval_ms": 1998.9, "decode_tok_per_s": 128.07, "load_ms": 326.0, "total_ms": 2479.5, "harness_wall_s": 2.483, "done_reason": "length" } ], "warmup": { "prompt_tokens": 318, "prompt_eval_ms": 96.4, "prefill_tok_per_s": 3298.64, "output_tokens": 256, "eval_ms": 2018.1, "decode_tok_per_s": 126.85, "load_ms": 328.7, "total_ms": 2578.7, "harness_wall_s": 2.582, "done_reason": "length" }, "summary": { "prefill_tok_per_s": { "min": 22372.04, "median": 23848.87, "max": 25397.83, "n": 3 }, "decode_tok_per_s": { "min": 128.05, "median": 128.07, "max": 128.76, "n": 3 }, "total_ms": { "min": 2461.3, "median": 2479.5, "max": 2500.0, "n": 3 } } }