Marin 535B-A23B Training at 7%, Team to Share Design Decisions and Tradeoffs
bariskasikci · x · 2026-08-28
Marin 535B-A23B is approximately 7% done training, and progress is on track. The team will host a Zoom panel next Tuesday (Sept 1 @ 10 PT) to discuss design decisions, tradeoffs, and learnings from this run. Join the Discord for more details.
More from Infra
- Autonomous launches $26,100 dual-RTX 5090 AI workstation, 'The Diablo' edition — dee_hw · 2026-08-28
- oMLX 0.6.3 Released: Qwen/GLM Flash Support, 160% Faster Decode — HankYeomans · 2026-08-28
- vLLM benchmarks MTP, EAGLE-3, and other speculative decoding methods on AMD GPUs — vllm_project · 2026-08-28
- Data center revenue drives $79M rate cut plan by US utility I&M — toptickcrypto · 2026-08-28
- Why AI data centers still rely on water cooling over air cooling? — wren337 · 2026-08-28
- Microsoft Tutorial: Configure AI Gateway in Foundry Resources — adnan_hashmi · 2026-08-28