Jackrong
Jackrong

Qwen3.5-9B (GLM-5.1 Distill) v1 benchmark on a NVIDIA's logo.GeForce RTX 5070 Ti

<- Runs

Prompt tokens

40,960

Generation tokens

10,240

Trials passed

10/10

Verified

73.8 tok/s

5,199.5 tok/s

Peak memory

9.22/23 GB

Runs well

Trials

Decode / Prefill Speeds

Metadata

metadata.json
{
"runId": "run_f7283e6b-5695-49bf-aa31-48c786656c90",
"bundleId": "llamacpp-qwen3.5-9b-glm5.1-distill-v1-q8_0.gguf-86b86d",
"status": "verified",
"promptTokens": 40960,
"completionTokens": 10240,
"contextLength": 5120,
"harness": {
"version": "0.1.21",
"gitSha": "unknown"
},
"runtime": {
"name": "llama.cpp",
"version": "b8849",
"buildFlags": "metal"
},
"model": {
"displayName": "Qwen3.5-9B (GLM-5.1 Distill) v1",
"format": "gguf",
"quant": "q8_0",
"architecture": "qwen35",
"source": "Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1-GGUF:Qwen3.5-9B-GLM5.1-Distill-v1-Q8_0.gguf",
"fileSizeBytes": 9527497984,
"lab": {
"name": "Jackrong",
"slug": "jackrong"
},
"quantizedBy": {
"name": "Jackrong",
"slug": "jackrong"
}
},
"device": {
"cpu": "Intel(R) Core(TM) Ultra 7 265KF",
"cpuCores": 20,
"gpu": "NVIDIA GeForce RTX 5070 Ti",
"gpuCores": 0,
"gpuCount": 1,
"ramGb": 23,
"osName": "Fedora Remix for WSL",
"osVersion": "Unknown"
},
"decodeTpsMean": 73.8,
"prefillTpsMean": 5199.5,
"ttftP50Ms": 787.74,
"idleTpsMean": 1635,
"peakRssMb": 9445.2,
"trialsPassed": 10,
"trialsTotal": 10,
"runnabilityScore": 0.7888274262422361,
"bundleSha256": "bbd1de9d755e897469698126c605d1d44cd652a11dc213679daf49adfbdd00c4",
"createdAt": "2026-04-19T17:52:17.927Z"
}