{ "schemaVersion": "1.0.0", "runId": "qwen38-27b-q4km-rtx4090-f16kv-8192-1787105510", "model": { "id": "qwen3.8-27b", "repository": "Qwen/Qwen3.8-27B", "revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0" }, "artifact": { "filename": "Qwen3.8-27B-Q4_K_M.gguf", "repository": "unsloth/Qwen3.8-27B-GGUF", "revision": "f1bfb127c64f7072bdd2cad55f258b9c8b2910fe", "sha256": "7e78da5d7e3ae28d178121f58646953305f3e5bd3cb46f4a75584e8b6c6fe169", "sizeBytes": 17106775008, "quantization": "q4-k-m", "contentHashSource": "Hugging Face x-linked-etag and independent local SHA-256" }, "runtime": { "name": "llama.cpp", "version": "version: 0.1.2-dev (build 1, commit 6d0549831)", "commit": "6d05498314db1b57f81c271080018aa2d0b89be9", "command": [ "/kingy-local-lab/llama.cpp/build/bin/llama-server", "-m", "/kingy-local-lab/models/Qwen3.8-27B-Q4_K_M.gguf", "-c", "8192", "-ngl", "999", "-ctk", "f16", "-ctv", "f16", "-b", "512", "-ub", "512", "--parallel", "1", "--host", "127.0.0.1", "--port", "8080", "--metrics", "--no-mmap" ] }, "environment": { "os": "Linux-6.14.0-29-generic-x86_64-with-glibc2.39", "hardware": "NVIDIA GeForce RTX 4090", "hardwareId": "rtx-4090-24gb", "gpuUuid": "GPU-26f05cd8-3563-5afe-e659-1dcadfa30718", "driverVersion": "580.65.06", "memoryBytes": 134217728000, "environmentLog": "logs/environment.txt", "cloudProvider": "RunPod Secure Cloud", "cloudRegion": "EUR-IS-1", "podId": "dto9mj08pd9xy0", "allocatedVcpu": 64, "cpu": "AMD EPYC 7702 64-Core Processor", "hostVisibleCpuCount": 256, "hostVisibleMemoryBytes": 540790554624, "allocationSource": "RunPod console: 64 vCPU and 125 GB; host-visible values retained separately", "gpuMemoryMiB": 24564, "cudaDriverCapability": "13.0", "cudaToolkit": "12.8.93" }, "configuration": { "contextTokens": 8192, "kvCacheType": "f16", "batchSize": 512, "microBatchSize": 512, "parallelism": 1, "gpuLayersRequested": 999, "offload": "all model layers and KV cache on GPU; no CPU layer offload", "phase": "fixed" }, "measurements": { "warmupRuns": 1, "measuredRuns": 3, "peakMemoryBytes": 17418944512, "peakMemoryMiB": 16612, "loadSeconds": 5.673754267394543, "promptTokensPerSecond": 2036.8872931125297, "generationTokensPerSecond": 47.72116865203187, "timeToFirstTokenSeconds": 0.2587182894349098, "outcome": "success", "actualPromptTokens": [ 512, 512, 512 ], "actualGenerationTokens": [ 128, 128, 128 ], "rawRepeats": [ { "label": "measured-1", "startedAt": "2026-08-19T02:11:43.112152Z", "timeToFirstTokenSeconds": 0.2586691938340664, "elapsedSeconds": 2.919361799955368, "eventCount": 129, "final": { "index": 0, "content": "", "tokens": [], "id_slot": 0, "stop": true, "model": "/kingy-local-lab/models/Qwen3.8-27B-Q4_K_M.gguf", "tokens_predicted": 128, "tokens_evaluated": 512, "generation_settings": { "seed": 42, "temperature": 0, "dynatemp_range": 0, "dynatemp_exponent": 1, "top_k": 20, "top_p": 0.949999988079071, "min_p": 0.05000000074505806, "top_n_sigma": -1, "xtc_probability": 0, "xtc_threshold": 0.10000000149011612, "typical_p": 1, "repeat_last_n": 64, "repeat_penalty": 1, "presence_penalty": 0, "frequency_penalty": 0, "dry_multiplier": 0, "dry_base": 1.75, "dry_allowed_length": 2, "dry_penalty_last_n": 64, "dry_sequence_breakers": [ "\n", ":", "\"", "*" ], "mirostat": 0, "mirostat_tau": 5, "mirostat_eta": 0.10000000149011612, "adaptive_target": -1, "adaptive_decay": 0.8999999761581421, "stop": [], "max_tokens": 128, "n_predict": 128, "n_keep": 0, "n_discard": 0, "ignore_eos": false, "stream": true, "logit_bias": [], "n_probs": 0, "min_keep": 0, "grammar": "", "grammar_lazy": false, "grammar_triggers": [], "preserved_tokens": [], "chat_format": "Content-only", "reasoning_format": "deepseek", "reasoning_in_content": false, "generation_prompt": "", "samplers": [ "penalties", "dry", "top_n_sigma", "top_k", "typ_p", "top_p", "min_p", "xtc", "temperature" ], "speculative.types": "none", "timings_per_token": false, "post_sampling_probs": false, "backend_sampling": false, "lora": [] }, "prompt": " benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark", "has_new_line": false, "truncated": false, "stop_type": "limit", "stopping_word": "", "tokens_cached": 639, "timings": { "cache_n": 0, "prompt_n": 512, "prompt_ms": 251.47, "prompt_per_token_ms": 0.49115234375, "prompt_per_second": 2036.0281544518232, "predicted_n": 128, "predicted_ms": 2659.998, "predicted_per_token_ms": 20.944866141732284, "predicted_per_second": 47.74439680029835 } } }, { "label": "measured-2", "startedAt": "2026-08-19T02:11:46.030639Z", "timeToFirstTokenSeconds": 0.25660601630806923, "elapsedSeconds": 2.918201819062233, "eventCount": 129, "final": { "index": 0, "content": "", "tokens": [], "id_slot": 0, "stop": true, "model": "/kingy-local-lab/models/Qwen3.8-27B-Q4_K_M.gguf", "tokens_predicted": 128, "tokens_evaluated": 512, "generation_settings": { "seed": 42, "temperature": 0, "dynatemp_range": 0, "dynatemp_exponent": 1, "top_k": 20, "top_p": 0.949999988079071, "min_p": 0.05000000074505806, "top_n_sigma": -1, "xtc_probability": 0, "xtc_threshold": 0.10000000149011612, "typical_p": 1, "repeat_last_n": 64, "repeat_penalty": 1, "presence_penalty": 0, "frequency_penalty": 0, "dry_multiplier": 0, "dry_base": 1.75, "dry_allowed_length": 2, "dry_penalty_last_n": 64, "dry_sequence_breakers": [ "\n", ":", "\"", "*" ], "mirostat": 0, "mirostat_tau": 5, "mirostat_eta": 0.10000000149011612, "adaptive_target": -1, "adaptive_decay": 0.8999999761581421, "stop": [], "max_tokens": 128, "n_predict": 128, "n_keep": 0, "n_discard": 0, "ignore_eos": false, "stream": true, "logit_bias": [], "n_probs": 0, "min_keep": 0, "grammar": "", "grammar_lazy": false, "grammar_triggers": [], "preserved_tokens": [], "chat_format": "Content-only", "reasoning_format": "deepseek", "reasoning_in_content": false, "generation_prompt": "", "samplers": [ "penalties", "dry", "top_n_sigma", "top_k", "typ_p", "top_p", "min_p", "xtc", "temperature" ], "speculative.types": "none", "timings_per_token": false, "post_sampling_probs": false, "backend_sampling": false, "lora": [] }, "prompt": " benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark", "has_new_line": false, "truncated": false, "stop_type": "limit", "stopping_word": "", "tokens_cached": 639, "timings": { "cache_n": 0, "prompt_n": 512, "prompt_ms": 249.38, "prompt_per_token_ms": 0.4870703125, "prompt_per_second": 2053.0916673349907, "predicted_n": 128, "predicted_ms": 2660.9, "predicted_per_token_ms": 20.95196850393701, "predicted_per_second": 47.72821225901011 } } }, { "label": "measured-3", "startedAt": "2026-08-19T02:11:48.955343Z", "timeToFirstTokenSeconds": 0.26087965816259384, "elapsedSeconds": 2.9243116192519665, "eventCount": 129, "final": { "index": 0, "content": "", "tokens": [], "id_slot": 0, "stop": true, "model": "/kingy-local-lab/models/Qwen3.8-27B-Q4_K_M.gguf", "tokens_predicted": 128, "tokens_evaluated": 512, "generation_settings": { "seed": 42, "temperature": 0, "dynatemp_range": 0, "dynatemp_exponent": 1, "top_k": 20, "top_p": 0.949999988079071, "min_p": 0.05000000074505806, "top_n_sigma": -1, "xtc_probability": 0, "xtc_threshold": 0.10000000149011612, "typical_p": 1, "repeat_last_n": 64, "repeat_penalty": 1, "presence_penalty": 0, "frequency_penalty": 0, "dry_multiplier": 0, "dry_base": 1.75, "dry_allowed_length": 2, "dry_penalty_last_n": 64, "dry_sequence_breakers": [ "\n", ":", "\"", "*" ], "mirostat": 0, "mirostat_tau": 5, "mirostat_eta": 0.10000000149011612, "adaptive_target": -1, "adaptive_decay": 0.8999999761581421, "stop": [], "max_tokens": 128, "n_predict": 128, "n_keep": 0, "n_discard": 0, "ignore_eos": false, "stream": true, "logit_bias": [], "n_probs": 0, "min_keep": 0, "grammar": "", "grammar_lazy": false, "grammar_triggers": [], "preserved_tokens": [], "chat_format": "Content-only", "reasoning_format": "deepseek", "reasoning_in_content": false, "generation_prompt": "", "samplers": [ "penalties", "dry", "top_n_sigma", "top_k", "typ_p", "top_p", "min_p", "xtc", "temperature" ], "speculative.types": "none", "timings_per_token": false, "post_sampling_probs": false, "backend_sampling": false, "lora": [] }, "prompt": " benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark benchmark", "has_new_line": false, "truncated": false, "stop_type": "limit", "stopping_word": "", "tokens_cached": 639, "timings": { "cache_n": 0, "prompt_n": 512, "prompt_ms": 253.272, "prompt_per_token_ms": 0.494671875, "prompt_per_second": 2021.5420575507756, "predicted_n": 128, "predicted_ms": 2662.982, "predicted_per_token_ms": 20.96836220472441, "predicted_per_second": 47.69089689678714 } } } ], "failureDetail": "", "statistics": { "promptTokensPerSecond": { "min": 2021.5420575507756, "median": 2036.0281544518232, "max": 2053.0916673349907 }, "generationTokensPerSecond": { "min": 47.69089689678714, "median": 47.72821225901011, "max": 47.74439680029835 }, "timeToFirstTokenSeconds": { "min": 0.25660601630806923, "median": 0.2586691938340664, "max": 0.26087965816259384 } } }, "evaluation": null, "timestamp": "2026-08-19T02:11:33.743106Z", "evidenceState": "observed", "reviewer": "Kingy AI Local Lab evidence review", "rawEvidence": { "requestLog": "logs/raw-fixed-8192.json", "serverLog": "logs/server-fixed-8192.log", "memoryLog": "logs/memory-fixed-8192.csv", "archiveUrl": "/data/evidence/kingy-qwen38-4090-evidence.tgz", "archiveSha256": "028781080144a73a611a6b729edf1af8e8fd4173bd047ec3a3dfc4bab86359b9" }, "review": { "status": "passed", "reviewedAt": "2026-08-19T02:20:00Z", "checks": [ "artifact size and SHA-256 match the pinned Hugging Face revision response", "single NVIDIA GeForce RTX 4090 with 24,564 MiB reported by nvidia-smi", "llama.cpp commit, driver, CUDA, OS, CPU and memory evidence retained", "FP16 K/V cache, one slot and -ngl 999; no CPU layer offload fallback", "one warm-up and three measured repetitions for every successful context", "512 prompt tokens and 128 generated tokens in every measured success", "CUDA OOM failures and the 1,024-token boundary bracket retained" ], "limitations": [ "RunPod host allocation is not a retail desktop platform and may differ in CPU, thermals and power behavior", "llama.cpp ignored the artifact's extra blk.64/MTP tensors; quality was not evaluated", "the measured boundary is an allocated-context VRAM-fit boundary; successful requests used 512 prompt tokens and 128 generated tokens, not a near-full-context prompt", "the boundary is established for this exact artifact, runtime commit, FP16 KV cache and batch settings only", "the upstream base revision is a pinned model record; the GGUF conversion lineage to that exact base commit was not independently established" ] }, "receiptHash": "sha256:aa3fb4e5afec81b14d282228a02aab9a09d826a0668045809bb8857680fcc053" }