Llama 70B
part of Llama
3 statements across 3 episodes · 1 bullish · 1 bearish · 3 people on the record · first statement Dec 5, 2023 by Dylan Patel · said 13 times in 6 episodes since 2023 · across every show →
Mentions by year
brought up most by Yining Zhang (3), William Beauchamp (3), Rishabh Agarwal (2), Sarah Chieng (1), Dylan Patel (1)
tap a year for its mentions
2025 9 mentions in 3 episodes 3 per episode
- DeepSeek V3, SGLang, and the state of Open Model Inference in 2025 (Quantization, MoEs, Pricing)
- Outlasting Noam Shazeer, Crowdsourcing Chai AI w/ 1.4m DAU — with William Beauchamp, Chai Research
- The Magic of LLM Distillation — Rishabh Agarwal, Google DeepMind
- every mention in 2025, scene by scene →
2024 3 mentions in 2 episodes 2 per episode
2023 1 mention in 1 episode
Everything said about Llama 70B, oldest first
Dec 5, 2023 positive
Patel: Google TPU v5e is half the size of TPU v5p
“TPUv-V-V-E is, like the new one, but it's mostly, mostly an inference chip. It's a small chip. It's a little bit, it's about half the size of a TPUv-V-V. That chip, you know, you can get very good performance on, like, Of Lama, 70 B inference, right?”
Jan 19, 2025 negative
Jul 13, 2026 neutral
Biderman: Processing a Wikipedia article in Llama 70B consumes 80GB HBM
“If you take a Lama, a 70 B model, and you load one article from Wikipedia, which is a few tens of kilobytes, and you have the model read this The brain state of the model when reading this few tens of kilobytes is like, 80 gigabytes. 80 gigabytes on, on the HB…”