{ "model_id": "m1", "model_tag": "qwen3.5:9b", "box_class": "cpu-laptop", "started_utc": "2026-08-25T16:22:02Z", "nproc": 24, "num_predict": 256, "prompt_sha256": "90eedd0c53f9554ae3837674504fcb7090013d9a432a653352183c0f25a7ce5c", "nvidia_before": "0, 15 MiB, 0 %", "ollama_version": "0.32.15", "runs": [ { "ttft_ms": 255.92, "first_token_was_thinking": false, "wall_s": 34.9126, "eval_count": 256, "eval_duration_ns": 34654723000, "decode_tok_s": 7.387, "prompt_eval_count": 537, "prompt_eval_duration_ns": 252271000, "prefill_tok_s": 2128.663, "load_duration_ns": 544553, "total_duration_ns": 34910227231, "streamed_chunks": 239, "response_chars": 1040, "thinking_chars": 0, "done_reason": "length", "run": 1 }, { "ttft_ms": 258.06, "first_token_was_thinking": false, "wall_s": 34.3244, "eval_count": 256, "eval_duration_ns": 34062781000, "decode_tok_s": 7.516, "prompt_eval_count": 537, "prompt_eval_duration_ns": 253096000, "prefill_tok_s": 2121.725, "load_duration_ns": 743985, "total_duration_ns": 34320911790, "streamed_chunks": 239, "response_chars": 1040, "thinking_chars": 0, "done_reason": "length", "run": 2 }, { "ttft_ms": 258.98, "first_token_was_thinking": false, "wall_s": 34.754, "eval_count": 256, "eval_duration_ns": 34492974000, "decode_tok_s": 7.422, "prompt_eval_count": 537, "prompt_eval_duration_ns": 254588000, "prefill_tok_s": 2109.29, "load_duration_ns": 590983, "total_duration_ns": 34751413475, "streamed_chunks": 239, "response_chars": 1040, "thinking_chars": 0, "done_reason": "length", "run": 3 }, { "ttft_ms": 257.29, "first_token_was_thinking": false, "wall_s": 34.6237, "eval_count": 256, "eval_duration_ns": 34362130000, "decode_tok_s": 7.45, "prompt_eval_count": 537, "prompt_eval_duration_ns": 252474000, "prefill_tok_s": 2126.952, "load_duration_ns": 656344, "total_duration_ns": 34619298115, "streamed_chunks": 239, "response_chars": 1040, "thinking_chars": 0, "done_reason": "length", "run": 4 }, { "ttft_ms": 258.04, "first_token_was_thinking": false, "wall_s": 34.6192, "eval_count": 256, "eval_duration_ns": 34359131999, "decode_tok_s": 7.451, "prompt_eval_count": 537, "prompt_eval_duration_ns": 252309000, "prefill_tok_s": 2128.343, "load_duration_ns": 846154, "total_duration_ns": 34616182502, "streamed_chunks": 239, "response_chars": 1040, "thinking_chars": 0, "done_reason": "length", "run": 5 } ], "errors": [], "quantization": "Q4_K_M", "param_size": "9.7B", "family": "qwen35", "context_length": 262144, "think_mode": false, "think_note": "think:false accepted", "warmup_discarded": { "ttft_ms": 258.32, "first_token_was_thinking": false, "wall_s": 34.8532, "eval_count": 256, "eval_duration_ns": 34592665000, "decode_tok_s": 7.4, "prompt_eval_count": 537, "prompt_eval_duration_ns": 253537000, "prefill_tok_s": 2118.034, "load_duration_ns": 745988, "total_duration_ns": 34850732187, "streamed_chunks": 239, "response_chars": 1040, "thinking_chars": 0, "done_reason": "length" }, "ps_after_load": [ { "name": "qwen3.5:9b", "model": "qwen3.5:9b", "size": 6071601067, "digest": "6488c96fa5faab64bb65cbd30d4289e20e6130ef535a93ef9a49f42eda893ea7", "details": { "parent_model": "", "format": "gguf", "family": "qwen35", "families": [ "qwen35" ], "parameter_size": "9.7B", "quantization_level": "Q4_K_M" }, "expires_at": "2026-08-25T16:32:55.991613588Z", "size_vram": 0, "context_length": 4096 } ], "size_vram": 0, "size_total": 6071601067, "cpu_only_receipt": true, "peak_runner_rss_kb": 6967312, "peak_runner_rss_gib": 6.64, "peak_runner_threads": 31, "rss_samples": 338, "loadavg_during_runs": { "min": 2.64, "median": 3.74, "max": 4.02, "mean": 3.6, "samples": 338, "nproc": 24 }, "contention_suspected": false, "contention_note": "loadavg consistent with this bench owning the machine", "foreign_gpu_procs_during": "0, 15 MiB, 0 %", "derived": { "decode_tok_s": { "min": 7.387, "median": 7.45, "max": 7.516, "mean": 7.445, "n": 5 }, "ttft_ms": { "min": 255.92, "median": 258.04, "max": 258.98, "mean": 257.658, "n": 5 }, "wall_s": { "min": 34.3244, "median": 34.6237, "max": 34.9126, "mean": 34.647, "n": 5 }, "prefill_tok_s": { "min": 2109.29, "median": 2126.952, "max": 2128.663, "mean": 2122.995, "n": 5 }, "eval_count": { "min": 256, "median": 256, "max": 256, "mean": 256.0, "n": 5 } }, "cold_load": [ { "ttft_ms": 18401.6, "first_token_was_thinking": false, "wall_s": 18.4032, "eval_count": 1, "eval_duration_ns": 1000, "decode_tok_s": 1000000.0, "prompt_eval_count": 537, "prompt_eval_duration_ns": 14068782000, "prefill_tok_s": 38.17, "load_duration_ns": 4328486642, "total_duration_ns": 18401091532, "streamed_chunks": 1, "response_chars": 5, "thinking_chars": 0, "done_reason": "length", "wall_to_first_token_s": 18.4033, "ps_confirmed_empty_before": true, "load_duration_s": 4.3285 }, { "ttft_ms": 18367.01, "first_token_was_thinking": false, "wall_s": 18.369, "eval_count": 1, "eval_duration_ns": 1000, "decode_tok_s": 1000000.0, "prompt_eval_count": 537, "prompt_eval_duration_ns": 14045197000, "prefill_tok_s": 38.234, "load_duration_ns": 4317749444, "total_duration_ns": 18366481650, "streamed_chunks": 1, "response_chars": 5, "thinking_chars": 0, "done_reason": "length", "wall_to_first_token_s": 18.3691, "ps_confirmed_empty_before": true, "load_duration_s": 4.3177 } ], "cold_load_note": "PAGE-CACHE-WARM: no sudo to drop caches, so this is warm-disk reload, not a true cold read from NVMe.", "nvidia_after": "0, 15 MiB, 0 %", "ps_final": [ { "name": "qwen3.5:9b", "model": "qwen3.5:9b", "size": 6071601067, "digest": "6488c96fa5faab64bb65cbd30d4289e20e6130ef535a93ef9a49f42eda893ea7", "details": { "parent_model": "", "format": "gguf", "family": "qwen35", "families": [ "qwen35" ], "parameter_size": "9.7B", "quantization_level": "Q4_K_M" }, "expires_at": "2026-08-25T16:36:26.577181901Z", "size_vram": 0, "context_length": 4096 } ], "finished_utc": "2026-08-25T16:26:26Z" }