Models

The compiler writes one BASE_MODEL string. Inkling and Inkling-Small are Tinker’s own weights — they compile. Interaction models are a real-time research preview, not a hosted base_model, so they are not on this desk. Full hosted list: Tinker models.

Live catalog unavailable. The 14 curated base models below still compile.

Thinking Machines

Inklingthinkingmachines/Inkling · 975B-A41B · 64KThinking Machines’ own weights. Hybrid + audio + vision.For: Calibrated Forecasting · Formal Reasoning EnginesIntroducing InklingBuild

Inkling-Smallthinkingmachines/Inkling-Small · 276B-A12B · 64KTinker’s smaller Inkling. Latency-friendlier own-weights pick.For: Specialized Tool AgentsIntroducing Inkling-SmallBuild

Dense — every weight live

Qwen3.5-4BQwen/Qwen3.5-4B · 4B dense · 64KSmallest dense base model before you scale rank or data.For: any jobBuild

Qwen3-8BQwen/Qwen3-8B · 8B dense · 32KDense workhorse when you want every weight live in the loop.For: any jobBuild

Qwen3.5-9BQwen/Qwen3.5-9B · 9B dense + vision · 64KWhen the reward needs screenshots, diagrams, or Lean goals.For: any jobBuild

Qwen3.8-27BQwen/Qwen3.8-27B · 27B dense + vision · 64KCurrent dense mid-size on Tinker. Successor weight class to Qwen3.6-27B.For: any jobBuild

MoE — sparse-activate

Nemotron-3.5-Lightningnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · 30B-A3B · 64KLatency-first MoE. The current Lightning pick next to Nano.For: Specialized Tool AgentsBuild

Nemotron-3-Nanonvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 · 30B-A3B · 64KCheap active params, fast tool planning.For: Specialized Tool AgentsBuild

Qwen3.6-35B-A3BQwen/Qwen3.6-35B-A3B · 35B-A3B + vision · 64KDefault Tinker mid-size: thrifty experts.For: any jobBuild

GPT-OSS-20Bopenai/gpt-oss-20b · 21B-A3.6B · 32KOpen-weight MoE when you want GPT-OSS without the 120B bill.For: any jobBuild

GPT-OSS-120Bopenai/gpt-oss-120b · 117B-A5B · 32KThe GPT-OSS Tinker hosts for mid-size reasoning adapters.For: Calibrated ForecastingBuild

GLM-5.3zai-org/GLM-5.3:peft:262144 · 753B-A40B · 256KZ.AI on Tinker. Always-on chain of thought.For: Formal Reasoning EnginesBuild

Kimi-K2.6moonshotai/Kimi-K2.6 · 1T-A32B · 32KThe large-end model Tinker’s own FAQ names.For: Calibrated ForecastingBuild

DeepSeek-V3.1deepseek-ai/DeepSeek-V3.1 · large MoE · 32KHard jobs: small adapter on a huge base model.For: Formal Reasoning EnginesBuild