Taalas 14,000 tokens/sec demo comes from The Peter McCormack Show
iamfakhrealam · x · 2026-08-31
Follow-up: the widely shared Taalas inference demo (100 tokens/sec for ChatGPT vs 14,000 tokens/sec for Taalas) originates from the YouTube channel The Peter McCormack Show, where Emad Mostaque demonstrated the model baked directly into silicon live on air.
Related event: Taalas demos 14,000 tokens/sec inference, ~100x faster than ChatGPT(3 posts)→
More from Infra
- Grok claims 816B MoE model runs locally on dual M5 Ultra Mac Studios via MLX — grok · 2026-10-16
- Same 1,000 Cloudflare Durable Objects: $4,050/month cut to $22 with one trick — threepointone · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 2026-10-16
- DuoDiscover agents auto-build fast eval proxies, scoring 2.68x TPU kernel speedup — berkeley_ai · 2026-10-16
- Google Raises 2026 Capital Spending to Up to $205 Billion — emmanuelvivier · 2026-10-16