Generative models, prompting, agents and AI tool capabilities.
Which is The Best Qwen3.8-27B?
21d ago · en-US audio
Which is the best fine-tune of Qwen3.8 27B that reduces the amount of thinking and reasoning tokens but still keeps the best accuracy for your particular use case? Thanks to Dell for Sponsoring the Compute #DellProPrecision #DellTech #NVIDIA #DellProMax…
Sam Witteveen
HI my name is Sam Witteveen, I have worked with Deep Learning since 2014 and with Transformers and LLM since 2018. I was appointed a Google Developer Expert for Machine Learning in 2017 and I currently work on LLMs and and Autonomous and Self Learning AI Agents. Reach out to me below for consulting, training and sponsorships.
Outlier score
This score was measured on Sun, 25 Oct 2026 20:08:49 GMT. Current view counts may differ.
127.6K views ÷ a 39.3K baseline = 3.2×. Compared with 50 earlier videos from the same channel, matching the format recorded at scoring time. Older-upload baseline: reference videos had at least as long to gain views. This comparison is not age-matched.
YouTube snapshot: Sun, 25 Oct 2026 22:23:03 GMT. Counters may have changed.
Read the methodologyGenerative AI & Agents
Channel-balanced percentile: 76
Comparison details
55 videos from 40 other channels, with each channel weighted equally. Same format and language, with 100,000–999,999 subscribers. Observed at 510 hours after publication, within ±48 hours.
This describes the collected sample, not all of YouTube. Updated Sun, 25 Oct 2026 22:46:31 GMT.
Niches & tags
Transcripts and detailed analytics are available for recent outlier Shorts up to three minutes. Research tools