Inkling Open Source Release: Multimodal & Long Context
ChrissGPT · x · 2026-07-16
Thinking Machines has released the open-source model Inkling:
- 975B parameter MoE with 41B active parameters
- Natively supports text, image, and audio reasoning
- 1M token context window
- Pre-trained from scratch using 45 trillion multimodal tokens
- Weights released under Apache 2.0
The team also shared initial benchmark scores across various metrics, including AIME 2026, GPQA Diamond, SWE-bench Verified/Pro, Terminal-Bench, MCP Atlas, MMMU Pro, and VoiceBench.
More from Multimodal
- Gemini Flash 3.8 image-to-SVG test sparks claim SVG may replace image models in 18 months — Kyrannio · 2026-09-03
- Higgsfield's new Genjutsu motion-copy tool impresses: better than Kling motion control? — rheylew · 2026-09-03
- Team claims h3 max is the undisputed #1 frontier video model across benchmarks — isidentical · 2026-09-03
- Fable 5.1 makes three.js sites: faster and sharper, but taste still matters — repligate · 2026-09-03
- Possible open-source MiniMax H3 Max weights appear on Hugging Face, real-time on 8x B200 — BassNet · 2026-09-03
- Point-and-click adventure built by chaining Nano Banana 2, MiniMax H3 Max, SAM 3 and GPT-5.6 — yshan2u · 2026-09-03