Step 3.7 Flash Lands on Baseten
baseten · x · 2026-07-14
Baseten has added Step 3.7 Flash to its Model Library.
It is a 198B parameter sparse MoE model that activates 11B parameters per token. It supports native image and video inputs and features a 256K context window. Baseten highlights its suitability for visual reasoning, agentic coding, and long-context tasks.
Related event: Baseten Adds Step 3.7 Flash, Opens Trial(2 posts)→
More from Infra
- Encrypted GPT-2 speedrun challenges FHE inference: best is 3.031 s/token, goal sub-1s — tensorqt · 2026-10-27
- Open-source Latch compiles PyTorch into training megakernels, 2.75x faster on H100 — sguada · 2026-10-27
- NVIDIA claims HGX Rubin NVL8 delivers 10x tokens per megawatt vs B200 — thursdai_pod · 2026-10-27
- NVIDIA Claims HGX Rubin NVL8 Delivers 10x More Tokens per Megawatt Than B200 — thursdai_pod · 2026-10-27
- Together lets multiple LoRA post-training experiments share the same GPU capacity — togethercompute · 2026-10-27
- Commoditization dilemma: either human labor or GPUs become the commodity — _AustinCalvert_ · 2026-10-27