Inkling Released with Day-0 Inference Support
simonguozirui · x · 2026-07-16
Quoting content, Thinking Machines released Inkling today, along with:
- A multimodal model capable of reasoning over text, images, and audio
- Full weights open for fine-tuning on Tinker, also available on Inkling Playground
- Ecosystem already has Day-0 support, with inference stacks mentioning NVIDIA B200/B300, AMD MI350X/MI355X, native FP4 serving, unified kernel architecture, MTP, optimized attention, and heterogeneous KV cache
- The post also provides throughput numbers: 355 tok/s/user on 4×B200 + MTP
More from Infra
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Cloud release velocity scores: AWS 95, Azure 90, Google Cloud 82 — DavidLinthicum · 2026-10-27
- Selling a 5090 to scale local inference: one business weighs 5 hardware paths — Anarchaotic · 2026-10-27
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27