
How to run Inkling 2 Small
Bedrock, Vertex AI, or your own GPUs · Checked November 21, 2026
Inkling 2 Small has 594B parameters, so it needs about 1,426GB of GPU memory at full precision and about 713GB at FP8. A practical starting point is FP8 on 8x 141GB GPUs.
You have three ways to run it: a managed host that already serves it, your own GPUs in your cloud, or both behind one endpoint. Then you point your agents at it. Here is what each path takes.
Inkling 2 Small hardware requirements
| Precision | Memory needed | Smallest setup that fits |
|---|---|---|
| BF16 (full precision) | ~1,426GB | Multiple 8x H200 nodes (about 2) |
| FP8 | ~713GB | 8x 141GB GPUs (one H200 node) |
| 4-bit quantized | ~357GB | 8x 80GB GPUs (one H100 node) |
Our estimates: 594B parameters times bytes per parameter, plus 20% for the KV cache and the serving runtime. As a mixture-of-experts model, Inkling 2 Small activates only 17B per token, which makes it fast, but every expert still has to sit in memory. Using the full 1M-token context needs more. Check the model card for the precision the weights ship in and any recommended settings.
Where to run Inkling 2 Small
01Amazon Bedrock
Not confirmed as of November 21, 2026We could not confirm Inkling 2 Small in the Bedrock model catalog. To keep it in AWS anyway, serve it yourself on GPU instances in your account (EC2 or SageMaker) with the setup below, and check the Bedrock catalog again: new open models are added often.
02Google Cloud Vertex AI
Not confirmed as of November 21, 2026We could not confirm Inkling 2 Small in Vertex AI Model Garden. To keep it in Google Cloud, serve it yourself on GPUs in your project (GKE or Compute Engine) with the setup below.
03Self-host on your own GPUs
vLLM support confirmedDownload thinkingmachines/Inkling-2-Small from Hugging Face and serve it with an inference server that exposes an OpenAI-compatible endpoint. vLLM support it. Requires a vLLM nightly ahead of 0.35.0; follow the recipe requirements. vLLM recipe. Start with FP8 on 8x 141GB GPUs (one H200 node), then load-test with your real prompts before you size for production.
- Keep the endpoint private to your VPC, so prompts and payment data never leave your cloud.
- Read the Apache 2.0 license, which allows commercial use.
- Run two replicas or keep a hosted model as a fallback, so agents keep working during an upgrade.
Run Inkling 2 Small with Runtime
Serving the model is half the job. The other half is giving agents a safe place to use it. Runtime is the AI agent harness for payment and fintech teams, and it is model-neutral: connect Inkling 2 Small from Bedrock, Vertex AI, or your own endpoint, and your agents use it next to Claude, GPT, or Gemini.
- In your cloud. Runtime runs in your AWS, GCP, or Azure account or fully self-hosted, next to the model.
- Routed by evals. Evals show which steps Inkling 2 Small handles as well as a frontier model, so routine work moves to the cheaper model.
- Fallbacks. If your endpoint is down or slow, agents fall back to another model instead of stopping.
- Guardrails. Agents start read-only, wait for approval before money moves, and every run is recorded.
Harnesses that can drive Inkling 2 Small on Runtime:
Running Inkling 2 Small: FAQ
How much GPU memory does Inkling 2 Small need?
+
About 1426GB at BF16, 713GB at FP8, and 357GB at 4 bits. These are our estimates: the weights plus 20% headroom. Long contexts need more memory for the KV cache.
What is the cheapest way to self-host Inkling 2 Small?
+
Start with FP8 on 8x 141GB GPUs (one H200 node). Quantizing further saves memory but can cost accuracy, so test it on your own tasks first.
Is Inkling 2 Small available on Amazon Bedrock?
+
As of November 21, 2026, we could not confirm Inkling 2 Small in the Bedrock model catalog. You can still run it in your AWS account on your own GPU instances (EC2 or SageMaker) with vLLM.
Is Inkling 2 Small available on Google Vertex AI?
+
As of November 21, 2026, we could not confirm Inkling 2 Small in Vertex AI Model Garden. You can still run it in your Google Cloud project on your own GPUs (GKE or Compute Engine) with vLLM.
Can I use Inkling 2 Small with Runtime?
+
Yes. Runtime is model-neutral. Serve Inkling 2 Small from Bedrock, Vertex AI, or your own endpoint, connect it to Runtime, and agents use it through a harness like Claude Code. Your data stays in your cloud, and evals tell you which steps it can take over from a more expensive model.