{ "host": "matt-strix", "gpu": "AMD Strix Halo iGPU", "vram_gb": null, "model_alias": "gemma4:31b", "model_tag": "gemma4:31b", "prompt_key": "short", "prompt_chars": 78, "num_predict": 256, "num_ctx": 4096, "runs": [ { "prompt_tokens": 28, "prompt_eval_ms": 96.4, "prefill_tok_per_s": 290.33, "output_tokens": 256, "eval_ms": 24049.7, "decode_tok_per_s": 10.64, "load_ms": 169.4, "total_ms": 24372.6, "harness_wall_s": 24.428, "done_reason": "length" }, { "prompt_tokens": 28, "prompt_eval_ms": 96.0, "prefill_tok_per_s": 291.74, "output_tokens": 256, "eval_ms": 24046.4, "decode_tok_per_s": 10.65, "load_ms": 165.7, "total_ms": 24365.4, "harness_wall_s": 24.429, "done_reason": "length" }, { "prompt_tokens": 28, "prompt_eval_ms": 95.6, "prefill_tok_per_s": 292.74, "output_tokens": 256, "eval_ms": 24065.8, "decode_tok_per_s": 10.64, "load_ms": 164.3, "total_ms": 24385.6, "harness_wall_s": 24.432, "done_reason": "length" } ], "warmup": { "prompt_tokens": 28, "prompt_eval_ms": 207.0, "prefill_tok_per_s": 135.28, "output_tokens": 256, "eval_ms": 24181.8, "decode_tok_per_s": 10.59, "load_ms": 5509.8, "total_ms": 30028.6, "harness_wall_s": 30.082, "done_reason": "length" }, "summary": { "prefill_tok_per_s": { "min": 290.33, "median": 291.74, "max": 292.74, "n": 3 }, "decode_tok_per_s": { "min": 10.64, "median": 10.64, "max": 10.65, "n": 3 }, "total_ms": { "min": 24365.4, "median": 24372.6, "max": 24385.6, "n": 3 } } }