Audio-Text-to-Text
ONNX
Safetensors
English
Chinese
Model Optimizer
bailing_moe_v3_audio
audio
speech
automatic-speech-recognition
audio-understanding
audio-reasoning
speech-to-text
conversational
mixture-of-experts
quantized
nvfp4
fp4
4-bit precision
modelopt
blackwell
custom_code
Eval Results (legacy)
Eval Results
8-bit precision
Download evals/results/performance.csv from twangodev/Ming-3.0-audio-flash-NVFP4: direct link, hf CLI and curl.
- Browser
- Download file 516 Bytes
-
https://huggingface.co/twangodev/Ming-3.0-audio-flash-NVFP4/resolve/main/evals/results/performance.csv
- Command line
-
hf download hf://twangodev/Ming-3.0-audio-flash-NVFP4/evals/results/performance.csv
-
curl -L -o performance.csv https://huggingface.co/twangodev/Ming-3.0-audio-flash-NVFP4/resolve/main/evals/results/performance.csv
516 Bytes
| model,precision,workload,median_output_tokens_per_second,model_allocation_gib,context_tokens,client_concurrency,server_capacity,output_tokens,timed_requests,warmup_requests,trials,workload_sha256,evidence_id | |
| flash,NVFP4,text,954.6916914720821,71.51,2304,128,128,128,1024,1024,3,a4c3fdb6ac6c0bbf344e4cf93b03c1a91ae719b77f500bf47ccc7da2a12fb652,flash_performance | |
| flash,NVFP4,audio,1853.8569235041743,71.51,2304,128,128,128,1024,1024,3,c210481ac11f07faaa0b238e4df129b6de74a382d4f639dce0b9a7d2d04383e8,flash_performance | |