Thinking Machines ships Inkling 2 Small: 594B MoE multimodal model lands on HF
ariG23498 · x · 2026-11-13
Thinking Machines released Inkling 2 Small on Hugging Face, the next generation of its Inkling family: a 594B-total / 17B-active MoE model taking image + text input. The original Inkling was a 1T-parameter open multimodal LLM with native image/text/audio input, 1M context, trained on 45T tokens, shipped in BF16 and NVFP4 with speculative MTP layers, plus an Inkling-Small at 276B/12B. Transformers, SGLang, vLLM and llama.cpp all got day-0 support; the team positions it for domain adaptation via fine-tuning and a new wave of multimodal reasoning apps.
Related event: Thinking Machines open-sources Inkling 2 Small: 594B MoE under Apache 2.0(8 posts)→
More from Models
- Raon-1 nano tops consumer-GPU agent tests: 96/96 tasks, 187 tok/s at ~2GB Q4 — Kangwook_Lee · 2026-11-13
- Same harness, same rules: Argon used the code graph in 12/17 sessions, Opus only 4/17 — rseroter · 2026-11-13
- Massive eval table update benchmarks open-weight models across coding, finance, legal — siyan_zhao · 2026-11-13
- Did Kimi K3 and DeepSeek-V4-Pro each train on 2,000-3,000 Blackwells? Claim disputed — teortaxesTex · 2026-11-13
- Community notes: Ling's Blackwell usage was an open secret, papers admitted renting compute — teortaxesTex · 2026-11-13
- Gemini 4 Hydrogen hits frontier-level scores at 1/3 the cost of Anthropic's flagship — Electronic-Weekend66 · 2026-11-13