{ "host": "matt-strix", "gpu": "AMD Strix Halo iGPU", "vram_gb": null, "model_alias": "gemma4:26b", "model_tag": "gemma4:26b", "prompt_key": "long", "prompt_chars": 1614, "num_predict": 256, "num_ctx": 4096, "runs": [ { "prompt_tokens": 319, "prompt_eval_ms": 22.5, "prefill_tok_per_s": 14201.36, "output_tokens": 256, "eval_ms": 4883.4, "decode_tok_per_s": 52.42, "load_ms": 151.1, "total_ms": 5120.3, "harness_wall_s": 5.186, "done_reason": "length" }, { "prompt_tokens": 319, "prompt_eval_ms": 22.1, "prefill_tok_per_s": 14448.45, "output_tokens": 256, "eval_ms": 4881.1, "decode_tok_per_s": 52.45, "load_ms": 159.1, "total_ms": 5124.5, "harness_wall_s": 5.18, "done_reason": "length" }, { "prompt_tokens": 319, "prompt_eval_ms": 22.3, "prefill_tok_per_s": 14326.07, "output_tokens": 256, "eval_ms": 4885.3, "decode_tok_per_s": 52.4, "load_ms": 155.4, "total_ms": 5128.9, "harness_wall_s": 5.192, "done_reason": "length" } ], "warmup": { "prompt_tokens": 319, "prompt_eval_ms": 265.0, "prefill_tok_per_s": 1203.86, "output_tokens": 256, "eval_ms": 4880.6, "decode_tok_per_s": 52.45, "load_ms": 159.8, "total_ms": 5368.3, "harness_wall_s": 5.429, "done_reason": "length" }, "summary": { "prefill_tok_per_s": { "min": 14201.36, "median": 14326.07, "max": 14448.45, "n": 3 }, "decode_tok_per_s": { "min": 52.4, "median": 52.42, "max": 52.45, "n": 3 }, "total_ms": { "min": 5120.3, "median": 5124.5, "max": 5128.9, "n": 3 } } }