Inkling

Facts

Released

2026-07-14 the day the repository was first published on Hugging Face Hugging Face, read 2026-09-24

Licence

apache-2.0 the licence the model card declares Hugging Face, read 2026-09-24

Open weights

Yes the weights are published in this Hugging Face repository Hugging Face, read 2026-09-24

Parameters

952.4 billion counted from the safetensors weight files Hugging Face, read 2026-09-24

Active parameters

18.1 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read 2026-09-24

Knowledge cutoff

Unknown

Context window

• 1,048,576 tokens the context length OpenRouter lists OpenRouter, read 2026-09-24

Longest output

• 471,859 tokens the largest output OpenRouter's first provider allows OpenRouter, read 2026-09-24

Tool calling

• Yes OpenRouter lists tools among the supported parameters OpenRouter, read 2026-09-24

Structured output

• No OpenRouter lists no structured output parameter OpenRouter, read 2026-09-24

Reasoning controls

• Yes OpenRouter lists reasoning controls, with the efforts max, high, medium, low, minimal, none OpenRouter, read 2026-09-24

Inputs and outputs

text, image in, text out Hugging Face, read 2026-09-24

Good for

• Vision: Hugging Face files it under image-text-to-text Hugging Face, read 2026-09-24
• Reasoning: OpenRouter lists reasoning controls for it OpenRouter, read 2026-09-24

Prices

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

Start it with a local runtime

• Ollama

  ollama run hf.co/unsloth/inkling-GGUF:UD-IQ1_S

• LM Studio

  lms get unsloth/inkling-GGUF
  lms server start

• llama.cpp server

  llama-server -hf unsloth/inkling-GGUF:UD-IQ1_S --jinja

• vLLM

  vllm serve thinkingmachines/Inkling

• SGLang

  sglang serve --model-path thinkingmachines/Inkling --port 30000

Use it from your harness

Set up for Abacus with the model thinkingmachines/Inkling. Each endpoint page has the same setup for its own address.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "abacus": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Abacus",
      "options": {
        "baseURL": "https://routellm.abacus.ai/v1",
        "apiKey": "{env:ABACUS_API_KEY}"
      },
      "models": {
        "thinkingmachines/Inkling": {
          "name": "Inkling",
          "limit": {
            "context": 1048576,
            "output": 471859
          }
        }
      }
    }
  }
}

{
  "providers": {
    "abacus": {
      "baseUrl": "https://routellm.abacus.ai/v1",
      "api": "openai-completions",
      "apiKey": "$ABACUS_API_KEY",
      "models": [
        {
          "id": "thinkingmachines/Inkling"
        }
      ]
    }
  }
}

Other ways to reach it

• Baseten, model thinkingmachines/inkling
• DeepInfra, model thinkingmachines/Inkling
• Hugging Face, model thinkingmachines/Inkling
• Impossibl, model thinkingmachines/inkling
• Kilo Gateway, model thinkingmachines/inkling
• LLMTR, model thinkingmachines/inkling
• NanoGPT, model thinkingmachines/inkling
• Nvidia, model thinkingmachines/inkling
• OpenRouter, model thinkingmachines/inkling
• Together AI, model thinkingmachines/Inkling

Published results

These are results other people published. Baltor did not run them and does not rank models by them.

• Results the maker published on the model card published by thinkingmachines Hugging Face, read 2026-09-24
• Artificial Analysis Intelligence Index: 25 published by Artificial Analysis OpenRouter, read 2026-09-24
• Artificial Analysis Coding Index: 52.1 published by Artificial Analysis OpenRouter, read 2026-09-24
• Artificial Analysis Agentic Index: 22.5 published by Artificial Analysis OpenRouter, read 2026-09-24