Thinking Machines' Inkling 2 Small hits Ollama: 594B MoE, 1M context
ollama · x · 2026-11-13
Thinking Machines Lab's Inkling 2 Small is now available on Ollama with zero data retention. The mixture-of-experts model has 594B total / 17B active parameters, accepts text and image input, offers a 1M-token context window, and targets agentic coding, research, and knowledge work, with variable reasoning effort and MCP tool calling.
Pricing is $0.30 per 1M input tokens ($0.03 cached) and $1.00 output. Run it via ollama run inkling-2-small:cloud; integrations include Claude Code, OpenCode, Hermes Agent, and OpenClaw. Cited use cases: OCR, grounding, infographic interpretation, visual reasoning, and finance/quantitative reasoning.
Related event: Thinking Machines' Inkling 2 Small lands on Ollama with 1M context(2 posts)→
More from Models
- DeepMind unveils Gemini Robotics 2.5: robots tie bows autonomously, 96% pick-and-pack success at Mercedes-Benz — AI_Andrew · 2026-11-13
- Unverified claims: OpenAI's Astra 6 held back by misalignment, Astra 6.1 reportedly cancelled — haider1 · 2026-11-13
- Claude Fable 5.2's 950K-Character System Prompt Leaked: 128 Tools, Hidden Mythos Tier Exposed — 新智元 · 2026-11-13
- LatentSpace's first model review: Naive-N0.5-Flash beats DeepSeek on coding, hits 2100 tokens/s — 量子位 · 2026-11-13
- Artificial Analysis Scores Qwen3.8-Flash-Next at 29, Between GPT-6 Luna Max and Haiku 5.5 — lionellee77 · 2026-11-13
- User finds Claude Opus 5.5 more creative and intuitive than Fable 5.2 — RileyRalmuto · 2026-11-13