Reproducible measurements

Compare test conditions before results

This page preserves the context and missing fields of public results so teams can establish their own capacity baseline.

Records: 3
Verified: 2026-07-26

Not directly comparable

RTFx changes with hardware, audio distribution, VAD, concurrency, warmup, and timing boundaries. A result missing any condition is not a procurement or capacity promise.

Fix inputs

Record total duration, file distribution, language, channels, and sample rate.

Fix system

Record CPU/GPU, driver, model, commit, runtime, and every parameter.

Define timing

State whether loading, warmup, I/O, queueing, and post-processing are included.

Public records

Read every number with its qualifications

vLLM GPU throughput

Fun-ASR-Nano-2512

RTFx 340; CER 8.20%

Runtime: vLLM batch
Hardware: GPU model not recorded in the cited public table
Workload: Offline batch
Audio: 184 long-form files; 11,541 seconds
Settings: Dynamic VAD; the public table does not record batch size or the full software and hardware stack
Timing scope: Offline throughput; the cited table does not state whether warmup, file I/O, and decoding are excluded
Verified: 2026-07-26

Qualification: Incomplete hardware and timing record. Use only as public reference evidence, not a capacity promise.

Open primary source

llama.cpp / GGUF standalone

SenseVoiceSmall Q8 GGUF

Approximately 20x realtime; Q8 CER 8.17%

Runtime: llama.cpp/GGUF with built-in FSMN-VAD
Hardware: CPU, 8 threads; CPU model not recorded in the cited report
Workload: Offline Mandarin CPU
Audio: 184 Mandarin clips, about 44-60 seconds each; total duration not recorded in the cited report
Settings: Q8 runtime; built-in FSMN-VAD; micro-CER normalize_zh; model load excluded
Timing scope: Sum of compute time divided by sum of audio duration; model load excluded
Verified: 2026-07-26

Qualification: CPU model and full software stack are not recorded. Reproduce on target hardware before comparison.

Open primary source

llama.cpp / GGUF standalone

Paraformer Q8 GGUF

Approximately 21x realtime; Q8 CER 9.89%

Runtime: llama.cpp/GGUF with built-in FSMN-VAD
Hardware: CPU, 8 threads; CPU model not recorded in the cited report
Workload: Offline Mandarin CPU
Audio: 184 Mandarin clips, about 44-60 seconds each; total duration not recorded in the cited report
Settings: Q8 runtime; built-in FSMN-VAD; micro-CER normalize_zh; model load excluded
Timing scope: Sum of compute time divided by sum of audio duration; model load excluded
Verified: 2026-07-26

Qualification: CPU model and full software stack are not recorded. Reproduce on target hardware before comparison.

Open primary source

Realtime services

Streaming capacity needs a separate test

File throughput does not describe draft latency, final latency, long-lived connection concurrency, or backpressure. Use the realtime WebSocket method to record them.

Realtime test method Offline RTFx method