Creators cited with this
Techno TimYouTube, 339K followers“For comparison, the dense Qwen 27B model I was testing was around 43.5 tokens per second.”
Watch the video at 2:15
Creators who use this also use
Qwen3.6-35B-A3B-FP8
also used by 1 of them
Stable Diffusion
also used by 1 of them
TensorFlow
also used by 1 of them
vLLM
also used by 1 of them
vLLM Semantic Router
also used by 1 of them
Whisper
also used by 1 of them