{ "model_id": "m4", "model_tag": "mistral-small3.2:24b", "box_class": "cpu-laptop", "started_utc": "2026-08-25T16:45:24Z", "nproc": 24, "num_predict": 256, "prompt_sha256": "90eedd0c53f9554ae3837674504fcb7090013d9a432a653352183c0f25a7ce5c", "nvidia_before": "0, 15 MiB, 0 %", "ollama_version": "0.32.15", "runs": [ { "ttft_ms": 376.71, "first_token_was_thinking": false, "wall_s": 95.0786, "eval_count": 256, "eval_duration_ns": 94700100000, "decode_tok_s": 2.703, "prompt_eval_count": 1023, "prompt_eval_duration_ns": 371412000, "prefill_tok_s": 2754.354, "load_duration_ns": 498372, "total_duration_ns": 95076373025, "streamed_chunks": 256, "response_chars": 1036, "thinking_chars": 0, "done_reason": "length", "run": 1 }, { "ttft_ms": 376.38, "first_token_was_thinking": false, "wall_s": 95.1198, "eval_count": 256, "eval_duration_ns": 94740224000, "decode_tok_s": 2.702, "prompt_eval_count": 1023, "prompt_eval_duration_ns": 371016000, "prefill_tok_s": 2757.293, "load_duration_ns": 957728, "total_duration_ns": 95116298696, "streamed_chunks": 256, "response_chars": 1036, "thinking_chars": 0, "done_reason": "length", "run": 2 }, { "ttft_ms": 376.58, "first_token_was_thinking": false, "wall_s": 95.0933, "eval_count": 256, "eval_duration_ns": 94713734000, "decode_tok_s": 2.703, "prompt_eval_count": 1023, "prompt_eval_duration_ns": 371694000, "prefill_tok_s": 2752.264, "load_duration_ns": 606799, "total_duration_ns": 95090072350, "streamed_chunks": 256, "response_chars": 1036, "thinking_chars": 0, "done_reason": "length", "run": 3 }, { "ttft_ms": 376.89, "first_token_was_thinking": false, "wall_s": 95.1642, "eval_count": 256, "eval_duration_ns": 94785515000, "decode_tok_s": 2.701, "prompt_eval_count": 1023, "prompt_eval_duration_ns": 371751000, "prefill_tok_s": 2751.842, "load_duration_ns": 613853, "total_duration_ns": 95161946097, "streamed_chunks": 256, "response_chars": 1036, "thinking_chars": 0, "done_reason": "length", "run": 4 }, { "ttft_ms": 375.97, "first_token_was_thinking": false, "wall_s": 95.1559, "eval_count": 256, "eval_duration_ns": 94778404000, "decode_tok_s": 2.701, "prompt_eval_count": 1023, "prompt_eval_duration_ns": 371105000, "prefill_tok_s": 2756.632, "load_duration_ns": 702744, "total_duration_ns": 95154015596, "streamed_chunks": 256, "response_chars": 1036, "thinking_chars": 0, "done_reason": "length", "run": 5 } ], "errors": [], "quantization": "Q4_K_M", "param_size": "24.0B", "family": "mistral3", "context_length": 131072, "think_mode": false, "think_note": "think:false accepted", "warmup_discarded": { "ttft_ms": 379.21, "first_token_was_thinking": false, "wall_s": 95.76, "eval_count": 256, "eval_duration_ns": 95377141000, "decode_tok_s": 2.684, "prompt_eval_count": 1023, "prompt_eval_duration_ns": 371780000, "prefill_tok_s": 2751.627, "load_duration_ns": 1047809, "total_duration_ns": 95755918545, "streamed_chunks": 256, "response_chars": 1036, "thinking_chars": 0, "done_reason": "length" }, "ps_after_load": [ { "name": "mistral-small3.2:24b", "model": "mistral-small3.2:24b", "size": 15305979984, "digest": "5a408ab55df5c1b5cf46533c368813b30bf9e4d8fc39263bf2a3338cfa3b895b", "details": { "parent_model": "", "format": "gguf", "family": "mistral3", "families": [ "mistral3" ], "parameter_size": "24.0B", "quantization_level": "Q4_K_M" }, "expires_at": "2026-08-25T16:58:31.41163779Z", "size_vram": 0, "context_length": 4096 } ], "size_vram": 0, "size_total": 15305979984, "cpu_only_receipt": true, "peak_runner_rss_kb": 15830552, "peak_runner_rss_gib": 15.1, "peak_runner_threads": 31, "rss_samples": 928, "loadavg_during_runs": { "min": 4.17, "median": 5.01, "max": 5.55, "mean": 4.85, "samples": 928, "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": 2.701, "median": 2.702, "max": 2.703, "mean": 2.702, "n": 5 }, "ttft_ms": { "min": 375.97, "median": 376.58, "max": 376.89, "mean": 376.506, "n": 5 }, "wall_s": { "min": 95.0786, "median": 95.1198, "max": 95.1642, "mean": 95.122, "n": 5 }, "prefill_tok_s": { "min": 2751.842, "median": 2754.354, "max": 2757.293, "mean": 2754.477, "n": 5 }, "eval_count": { "min": 256, "median": 256, "max": 256, "mean": 256.0, "n": 5 } }, "cold_load": [ { "ttft_ms": 91437.55, "first_token_was_thinking": false, "wall_s": 91.4387, "eval_count": 1, "eval_duration_ns": 1000, "decode_tok_s": 1000000.0, "prompt_eval_count": 1023, "prompt_eval_duration_ns": 82356393000, "prefill_tok_s": 12.422, "load_duration_ns": 9076392670, "total_duration_ns": 91437004851, "streamed_chunks": 1, "response_chars": 4, "thinking_chars": 0, "done_reason": "length", "wall_to_first_token_s": 91.4387, "ps_confirmed_empty_before": true, "load_duration_s": 9.0764 }, { "ttft_ms": 91434.35, "first_token_was_thinking": false, "wall_s": 91.4365, "eval_count": 1, "eval_duration_ns": 1000, "decode_tok_s": 1000000.0, "prompt_eval_count": 1023, "prompt_eval_duration_ns": 82351108000, "prefill_tok_s": 12.422, "load_duration_ns": 9078304937, "total_duration_ns": 91433835790, "streamed_chunks": 1, "response_chars": 4, "thinking_chars": 0, "done_reason": "length", "wall_to_first_token_s": 91.4366, "ps_confirmed_empty_before": true, "load_duration_s": 9.0783 } ], "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": "mistral-small3.2:24b", "model": "mistral-small3.2:24b", "size": 15305979984, "digest": "5a408ab55df5c1b5cf46533c368813b30bf9e4d8fc39263bf2a3338cfa3b895b", "details": { "parent_model": "", "format": "gguf", "family": "mistral3", "families": [ "mistral3" ], "parameter_size": "24.0B", "quantization_level": "Q4_K_M" }, "expires_at": "2026-08-25T17:09:30.819367817Z", "size_vram": 0, "context_length": 4096 } ], "finished_utc": "2026-08-25T16:59:31Z" }