{ "host": "matt-strix", "gpu": "AMD Strix Halo iGPU", "vram_gb": null, "model_alias": "gemma4:26b", "model_tag": "gemma4:26b", "prompt_key": "short", "prompt_chars": 78, "num_predict": 256, "num_ctx": 4096, "runs": [ { "prompt_tokens": 28, "prompt_eval_ms": 21.9, "prefill_tok_per_s": 1278.99, "output_tokens": 256, "eval_ms": 4754.7, "decode_tok_per_s": 53.84, "load_ms": 172.3, "total_ms": 5008.5, "harness_wall_s": 5.057, "done_reason": "length" }, { "prompt_tokens": 28, "prompt_eval_ms": 21.9, "prefill_tok_per_s": 1275.71, "output_tokens": 256, "eval_ms": 4755.7, "decode_tok_per_s": 53.83, "load_ms": 151.6, "total_ms": 4988.3, "harness_wall_s": 5.043, "done_reason": "length" }, { "prompt_tokens": 28, "prompt_eval_ms": 22.0, "prefill_tok_per_s": 1271.11, "output_tokens": 256, "eval_ms": 4757.6, "decode_tok_per_s": 53.81, "load_ms": 154.4, "total_ms": 4993.2, "harness_wall_s": 5.048, "done_reason": "length" } ], "warmup": { "prompt_tokens": 28, "prompt_eval_ms": 93.1, "prefill_tok_per_s": 300.9, "output_tokens": 256, "eval_ms": 4756.6, "decode_tok_per_s": 53.82, "load_ms": 2272.4, "total_ms": 7250.0, "harness_wall_s": 7.341, "done_reason": "length" }, "summary": { "prefill_tok_per_s": { "min": 1271.11, "median": 1275.71, "max": 1278.99, "n": 3 }, "decode_tok_per_s": { "min": 53.81, "median": 53.83, "max": 53.84, "n": 3 }, "total_ms": { "min": 4988.3, "median": 4993.2, "max": 5008.5, "n": 3 } } }