Qwen3.8 27B hits Cerebras Shared Tier at ~1500 tok/s
TheMoonMidas · x · 2026-09-04
Qwen3.8 27B is now available on Cerebras' Shared Tier at roughly 1500 tokens per second. The poster notes the model summarized their entire codebase faster than it took them to write the prompt.
Related event: Qwen3.8 27B hits 1500 tokens/s on Cerebras(2 posts)→
More from Infra
- Pichai: everyone is massively short on AI compute — 'everyone wishes you had two times what you had planned' — firstadopter · 2026-10-21
- Stanford CS336 Lecture 6: fused Triton kernels cut softmax memory traffic ~4x — stanfordnlp · 2026-10-21
- General Compute partners with Positron AI: Atlas memory-centric hardware ships Q1 2027 — aftahi_ai · 2026-10-21
- AI bond issuance hits $419B in 2026, up 90% from all of 2025 — SumitGup · 2026-10-21
- AI Obsession Is Making Enterprises Neglect Cloud FinOps, Expert Warns — DavidLinthicum · 2026-10-21
- DeepSeek bottleneck is compute, not demand: 1GW cluster could train a far stronger model, says leak account — teortaxesTex · 2026-10-21