{
 "case": "bench-q4_k_m",
 "machine": "windows-2022-nocuda",
 "run": "ci-1",
 "args": [
  "--model",
  "models\\qwen2.5-0.5b-instruct-q4_k_m.gguf",
  "--contextsize",
  "4096"
 ],
 "started": "2026-11-13T12:42:20+0000",
 "exit_code": 0,
 "seconds": 47.7,
 "bench_csv": "Timestamp,Backend,Layers,Model,MaxCtx,GenAmount,ProcessingTime,ProcessingSpeed,GenerationTime,GenerationSpeed,TotalTime,Output,Flags\n2026-11-13 12:43:07.855983+00:00,koboldcpp_default.dll,0,qwen2.5-0.5b-instruct-q4_k_m,4096,100,33.45,119.46,6.47,15.46,39.92, 1 1 1 1,\"{'usecuda': None, 'usevulkan': None, 'usecpu': False, 'model': ['models\\\\qwen2.5-0.5b-instruct-q4_k_m.gguf'], 'model_param': 'models\\\\qwen2.5-0.5b-instruct-q4_k_m.gguf', 'config': None, 'contextsize': 4096, 'gpulayers': 0, 'host': '', 'launch': False, 'tensor_split': None, 'threads': 2, 'port': 5001, 'port_param': 5001, 'version': False, 'agent': False, 'agentload': '', 'analyze': '', 'autofit': False, 'autofitpadding': 1024, 'batchsize': 512, 'ubatchsize': -1, 'benchmark': 'results\\\\ci-1\\\\windows-2022-nocuda\\\\bench-q4_k_m\\\\bench.csv', 'blasthreads': 2, 'chatcompletionsadapter': 'AutoGuess', 'cli': False, 'debugmode': 0, 'defaultgenamt': 2048, 'device': '', 'downloaddir': '', 'draftamount': 4, 'draftgpulayers': 999, 'draftgpusplit': None, 'draftmodel': '', 'enableguidance': False, 'exportconfig': '', 'exporttemplate': '', 'failsafe': False, 'foreground': False, 'gendefaults': '', 'gendefaultsoverwrite': False, 'genlimit': 0, 'highpriority': False, 'ignoremissing': False, 'jinja': False, 'jinja_kwargs': '', 'jinjatemplate': '', 'jinjathink': 'default', 'lora': None, 'loramult': 1.0, 'lowvram': False, 'maingpu': -1, 'maxrequestsize': 32, 'mcpfile': '', 'mmproj': '', 'mmprojcpu': False, 'lazy_mode': 'auto', 'moe_cache_mib': 0, 'moecpu': 0, 'ffncpu': 0, 'moeexperts': -1, 'multiplayer': False, 'nocertify': False, 'nofastforward': False, 'noflashattention': False, 'noavx2': False, 'nobostoken': False, 'nommq': False, 'nomodel': False, 'noshift': False, 'noswa': False, 'onready': '', 'allow_config_onready': False, 'overridekv': '', 'overridenativecontext': 0, 'overridetensors': '', 'parallelrequests': 1, 'paralleltotalcontext': 0, 'password': None, 'preloadstory': '', 'prompt': '', 'quantkv': 'f16', 'queuelimit': 10, 'quiet': False, 'ratelimit': 0, 'reasoningeffort': 'default', 'remotetunnel': False, 'ropeconfig': [0.0, 10000.0], 'savedatafile': '', 'singleinstance': False, 'smartcache': 0, 'smartcontext': False, 'splitmode': 'layer', 'ssl': None, 'swapadding': 0, 'unpack': '', 'usemtp': False, 'usemlock': False, 'usemmap': False, 'usedirectio': False, 'visionmaxres': 1024, 'visionmaxtokens': -1, 'visionmintokens': -1, 'websearch': False, 'showgui': False, 'skiplauncher': True, 'hordemodelname': '', 'hordeworkername': '', 'hordekey': '', 'hordemaxctx': 0, 'hordegenlen': 0, 'sdaudiovae': '', 'sdclamped': 0, 'sdclampedsoft': 0, 'sdclip1': '', 'sdclip2': '', 'sdclipdevice': -2, 'sdconvdirect': 'off', 'sdflashattention': False, 'sdlora': [], 'sdloramult': [1.0], 'sdmaingpu': None, 'sdmodel': '', 'sdoffloadcpu': False, 'sdphotomaker': '', 'sdquant': 0, 'sdllm': '', 'sdthreads': 0, 'sdtiledvae': 512, 'sdupscaler': '', 'sdvae': '', 'sdvaeauto': False, 'sdvaedevice': -1, 'sdvramlimit': 0, 'whispermodel': '', 'ttsmodel': '', 'ttswavtokenizer': '', 'ttsgpu': False, 'ttsmaxlen': 4096, 'ttsthreads': 0, 'ttsdir': '', 'musicllm': '', 'musicembeddings': '', 'musicdiffusion': '', 'musicvae': '', 'musiclowvram': False, 'embeddingsmodel': '', 'embeddingsmaxctx': 4096, 'embeddingsgpu': False, 'rpcmode': 'disabled', 'rpcport': 5551, 'rpchost': '0.0.0.0', 'rpcdevice': '', 'rpccache': '', 'rpctargets': '', 'admin': False, 'adminpassword': None, 'admindir': '', 'adminunloadtimeout': 0, 'routermode': False, 'reqtimeout': 600, 'autoswapmode': False, 'autoswapthreshold': 256, 'baseconfig': '', 'hordeconfig': None, 'sdconfig': None, 'noblas': False, 'nommap': False, 'nopipelineparallel': False, 'pipelineparallel': False, 'sdnotile': False, 'sdt5xxl': None, 'sdvaecpu': False, 'sdclipgpu': False, 'forceversion': False, 'sdgendefaults': False, 'flashattention': False, 'useswa': False, 'multiuser': None, 'testmemory': False, 'run_bundled_agent': False, 'agent_base_url': None, 'agent_api_key': None, 'proxy_port': None}\"\n",
 "log_lines": [
  "Unable to detect VRAM.",
  "Auto Selected Default Backend (flag=0)",
  "Unable to detect VRAM.",
  "Unable to determine GPU Memory",
  "Detected Available RAM: 13702 MB",
  "Initializing dynamic library: koboldcpp_default.dll",
  "Namespace(admin=False, admindir='', adminpassword=<redacted> adminunloadtimeout=0, agent=False, agent_api_key=<redacted> agent_base_url=None, agentload='', allow_config_onready=False, analyze='', autofit=False, autofitpadding=1024, autoswapmode=False, autoswapthreshold=256, baseconfig='', batchsize=512, benchmark='results\\\\ci-1\\\\windows-2022-nocuda\\\\bench-q4_k_m\\\\bench.csv', blasthreads=0, chatcompletionsadapter='AutoGuess', cli=False, config=None, contextsize=4096, debugmode=0, defaultgenamt=2048, device='', downloaddir='', draftamount=4, draftgpulayers=999, draftgpusplit=None, draftmodel='', embeddingsgpu=False, embeddingsmaxctx=4096, embeddingsmodel='', enableguidance=False, exportconfig='', exporttemplate='', failsafe=False, ffncpu=0, flashattention=False, forceversion=False, foreground=False, gendefaults='', gendefaultsoverwrite=False, genlimit=0, gpulayers=0, highpriority=False, hordeconfig=None, hordegenlen=0, hordekey='', hordemaxctx=0, hordemodelname='', hordeworkername='', host='', ignoremissing=False, jinja=False, jinja_kwargs='', jinjatemplate='', jinjathink='default', launch=False, lazy_mode='auto', lora=None, loramult=1.0, lowvram=False, maingpu=-1, maxrequestsize=32, mcpfile='', mmproj='', mmprojcpu=False, model=['models\\\\qwen2.5-0.5b-instruct-q4_k_m.gguf'], model_param='models\\\\qwen2.5-0.5b-instruct-q4_k_m.gguf', moe_cache_mib=0, moecpu=0, moeexperts=-1, multiplayer=False, multiuser=None, musicdiffusion='', musicembeddings='', musicllm='', musiclowvram=False, musicvae='', noavx2=False, noblas=False, nobostoken=<redacted> nocertify=False, nofastforward=False, noflashattention=False, nommap=False, nommq=False, nomodel=False, nopipelineparallel=False, noshift=False, noswa=False, onready='', overridekv='', overridenativecontext=0, overridetensors='', parallelrequests=1, paralleltotalcontext=0, password=<redacted> pipelineparallel=False, port=5001, port_param=5001, preloadstory='', prompt='', proxy_port=None, quantkv='f16', queuelimit=10, quiet=False, ratelimit=0, reasoningeffort='default', remotetunnel=False, reqtimeout=600, ropeconfig=[0.0, 10000.0], routermode=False, rpccache='', rpcdevice='', rpchost='0.0.0.0', rpcmode='disabled', rpcport=5551, rpctargets='', run_bundled_agent=False, savedatafile='', sdaudiovae='', sdclamped=0, sdclampedsoft=0, sdclip1='', sdclip2='', sdclipdevice=-2, sdclipgpu=False, sdconfig=None, sdconvdirect='off', sdflashattention=False, sdgendefaults=False, sdllm='', sdlora=[], sdloramult=[1.0], sdmaingpu=None, sdmodel='', sdnotile=False, sdoffloadcpu=False, sdphotomaker='', sdquant=0, sdt5xxl=None, sdthreads=0, sdtiledvae=512, sdupscaler='', sdvae='', sdvaeauto=False, sdvaecpu=False, sdvaedevice=-1, sdvramlimit=0, showgui=False, singleinstance=False, skiplauncher=True, smartcache=0, smartcontext=False, splitmode='layer', ssl=None, swapadding=0, tensor_split=None, testmemory=False, threads=2, ttsdir='', ttsgpu=False, ttsmaxlen=4096, ttsmodel='', ttsthreads=0, ttswavtokenizer='', ubatchsize=-1, unpack='', usecpu=False, usecuda=None, usedirectio=False, usemlock=False, usemmap=False, usemtp=False, useswa=False, usevulkan=None, version=False, visionmaxres=1024, visionmaxtokens=-1, visionmintokens=-1, websearch=False, whispermodel='')",
  "Threadpool set to 2 threads and 2 blasthreads...",
  "Processing Prompt (0 / 3996 tokens)",
  "Processing Prompt (512 / 3996 tokens)",
  "Processing Prompt (1024 / 3996 tokens)",
  "Processing Prompt (1536 / 3996 tokens)",
  "Processing Prompt (2048 / 3996 tokens)",
  "Processing Prompt (2560 / 3996 tokens)",
  "Processing Prompt (3072 / 3996 tokens)",
  "Processing Prompt (3584 / 3996 tokens)",
  "Processing Prompt (3996 / 3996 tokens)",
  "[12:43:07] CtxLimit:4096/4096, Init:0.10s, Processed:3996 in 33.45s (119.46T/s), Generated:100/100 in 6.47s (15.46T/s), Total:40.02sLoad Text Model OK: True",
  "Active Modules: TextGeneration",
  "Inactive Modules: ImageGeneration VoiceRecognition MultimodalVision MultimodalAudio NetworkMultiplayer ApiKeyPassword WebSearchProxy TextToSpeech VectorEmbeddings AdminControl MCPBridge MusicGen RouterMode",
  "Running benchmark (Save to File: results\\ci-1\\windows-2022-nocuda\\bench-q4_k_m\\bench.csv)...",
  "Benchmark Completed - v1.124.2 Results:",
  "Flags: {'usecuda': None, 'usevulkan': None, 'usecpu': False, 'model': ['models\\\\qwen2.5-0.5b-instruct-q4_k_m.gguf'], 'model_param': 'models\\\\qwen2.5-0.5b-instruct-q4_k_m.gguf', 'config': None, 'contextsize': 4096, 'gpulayers': 0, 'host': '', 'launch': False, 'tensor_split': None, 'threads': 2, 'port': 5001, 'port_param': 5001, 'version': False, 'agent': False, 'agentload': '', 'analyze': '', 'autofit': False, 'autofitpadding': 1024, 'batchsize': 512, 'ubatchsize': -1, 'benchmark': 'results\\\\ci-1\\\\windows-2022-nocuda\\\\bench-q4_k_m\\\\bench.csv', 'blasthreads': 2, 'chatcompletionsadapter': 'AutoGuess', 'cli': False, 'debugmode': 0, 'defaultgenamt': 2048, 'device': '', 'downloaddir': '', 'draftamount': 4, 'draftgpulayers': 999, 'draftgpusplit': None, 'draftmodel': '', 'enableguidance': False, 'exportconfig': '', 'exporttemplate': '', 'failsafe': False, 'foreground': False, 'gendefaults': '', 'gendefaultsoverwrite': False, 'genlimit': 0, 'highpriority': False, 'ignoremissing': False, 'jinja': False, 'jinja_kwargs': '', 'jinjatemplate': '', 'jinjathink': 'default', 'lora': None, 'loramult': 1.0, 'lowvram': False, 'maingpu': -1, 'maxrequestsize': 32, 'mcpfile': '', 'mmproj': '', 'mmprojcpu': False, 'lazy_mode': 'auto', 'moe_cache_mib': 0, 'moecpu': 0, 'ffncpu': 0, 'moeexperts': -1, 'multiplayer': False, 'nocertify': False, 'nofastforward': False, 'noflashattention': False, 'noavx2': False, 'nobostoken': False, 'nommq': False, 'nomodel': False, 'noshift': False, 'noswa': False, 'onready': '', 'allow_config_onready': False, 'overridekv': '', 'overridenativecontext': 0, 'overridetensors': '', 'parallelrequests': 1, 'paralleltotalcontext': 0, 'password': None, 'preloadstory': '', 'prompt': '', 'quantkv': 'f16', 'queuelimit': 10, 'quiet': False, 'ratelimit': 0, 'reasoningeffort': 'default', 'remotetunnel': False, 'ropeconfig': [0.0, 10000.0], 'savedatafile': '', 'singleinstance': False, 'smartcache': 0, 'smartcontext': False, 'splitmode': 'layer', 'ssl': None, 'swapadding': 0, 'unpack': '', 'usemtp': False, 'usemlock': False, 'usemmap': False, 'usedirectio': False, 'visionmaxres': 1024, 'visionmaxtokens': -1, 'visionmintokens': -1, 'websearch': False, 'showgui': False, 'skiplauncher': True, 'hordemodelname': '', 'hordeworkername': '', 'hordekey': '', 'hordemaxctx': 0, 'hordegenlen': 0, 'sdaudiovae': '', 'sdclamped': 0, 'sdclampedsoft': 0, 'sdclip1': '', 'sdclip2': '', 'sdclipdevice': -2, 'sdconvdirect': 'off', 'sdflashattention': False, 'sdlora': [], 'sdloramult': [1.0], 'sdmaingpu': None, 'sdmodel': '', 'sdoffloadcpu': False, 'sdphotomaker': '', 'sdquant': 0, 'sdllm': '', 'sdthreads': 0, 'sdtiledvae': 512, 'sdupscaler': '', 'sdvae': '', 'sdvaeauto': False, 'sdvaedevice': -1, 'sdvramlimit': 0, 'whispermodel': '', 'ttsmodel': '', 'ttswavtokenizer': '', 'ttsgpu': False, 'ttsmaxlen': 4096, 'ttsthreads': 0, 'ttsdir': '', 'musicllm': '', 'musicembeddings': '', 'musicdiffusion': '', 'musicvae': '', 'musiclowvram': False, 'embeddingsmodel': '', 'embeddingsmaxctx': 4096, 'embeddingsgpu': False, 'rpcmode': 'disabled', 'rpcport': 5551, 'rpchost': '0.0.0.0', 'rpcdevice': '', 'rpccache': '', 'rpctargets': '', 'admin': False, 'adminpassword': None, 'admindir': '', 'adminunloadtimeout': 0, 'routermode': False, 'reqtimeout': 600, 'autoswapmode': False, 'autoswapthreshold': 256, 'baseconfig': '', 'hordeconfig': None, 'sdconfig': None, 'noblas': False, 'nommap': False, 'nopipelineparallel': False, 'pipelineparallel': False, 'sdnotile': False, 'sdt5xxl': None, 'sdvaecpu': False, 'sdclipgpu': False, 'forceversion': False, 'sdgendefaults': False, 'flashattention': False, 'useswa': False, 'multiuser': None, 'testmemory': False, 'run_bundled_agent': False, 'agent_base_url': None, 'agent_api_key': None, 'proxy_port': None}",
  "ProcessingTime: 33.451s",
  "ProcessingSpeed: 119.46T/s",
  "GenerationTime: 6.468s",
  "GenerationSpeed: 15.46T/s",
  "Output:  1 1 1 1",
  "print_info: file size   = 462.96 MiB (6.16 BPW)",
  "print_info: n_ctx_train           = 32768",
  "print_info: n_ctx_orig_yarn       = 32768",
  "done_getting_tensors: tensor 'token_embd.weight' (q5_0) (and 278 others) moved from CPU_REPACK, using CPU instead",
  "load_tensors:          CPU model buffer size =   434.91 MiB",
  "load_tensors:   CPU_REPACK model buffer size =    28.05 MiB",
  "llama_context: n_ctx                 = 4352",
  "llama_context: n_ctx_seq             = 4352",
  "llama_context: flash_attn            = enabled",
  "llama_context: n_outputs_max         = 512",
  "llama_context: n_outputs_max_per_seq = 1",
  "llama_context: n_ctx_seq (4352) < n_ctx_train (32768) -- the full capacity of the model will not be utilized"
 ],
 "finished": "2026-11-13T12:43:08+0000"
}