SovAIHub
Resources
Free Tool

Hardware-to-Model Matchmaker

Pick your GPU — or enter your VRAM — and see exactly which open-weight models you can self-host, at which quantization, with how much headroom. All models listed are fully sovereign: open weights, self-hosted, zero external API calls.

Hardware and workload

Models that fit your hardware

Best (least lossy) quantization that fits is shown. Larger models are listed first.

ModelLicenseContextQuantizationNeedsHeadroomRuntimes
Gemma 2 27B
Gemma Terms of Use8KQ422 GB8%Ollama · vLLM
StarCoder2 15B
BigCode OpenRAIL-M16KINT822 GB9%Ollama · vLLM
Code Llama 13B
Llama 2 Community License16KINT820 GB19%Ollama · vLLM
Mistral Nemo 12B
Long-context document intelligence at mid size.
Apache-2.0128KINT819 GB24%Ollama · vLLM
Gemma 2 9B
Strong reasoning; short 8K context.
Gemma Terms of Use8KINT815 GB39%Ollama · vLLM
Llama 3.1 8B
The default starting point for private RAG on a single GPU.
Llama 3.1 Community License128KFP1623 GB6%Ollama · vLLM · OpenShift AI
Mistral 7B
Efficient permissively-licensed baseline.
Apache-2.032KFP1621 GB15%Ollama · vLLM · Docker
Qwen 2.5 7B
Apache-2.0128KFP1621 GB15%Ollama · vLLM
Phi-3.5 Mini (3.8B)
Runs on laptops and edge devices; excellent quality-to-size ratio.
MIT128KFP1613 GB46%Ollama · Edge · Docker

Needs more memory

Minimum requirement shown at the smallest common quantization with your context and concurrency.

DeepSeek R1 Distill 32B

Needs ≈ 26 GB at Q4

Mixtral 8×7B

Needs ≈ 36 GB at Q4

Llama 3.1 70B

Needs ≈ 51 GB at Q4

Qwen 2.5 72B

Needs ≈ 52 GB at Q4

Llama 3.1 405B

Needs ≈ 274 GB at Q4

DeepSeek R1 (671B MoE)

Needs ≈ 451 GB at Q4

Don't own the hardware yet? Rent it by the hour first.

Before buying GPUs, validate your model choice on rented hardware. Run your actual workload for a few dollars, measure tokens/sec, then size your on-prem purchase with real numbers.

Email me these results + sovereign AI deployment notes

Get your hardware match summary and occasional practical notes on self-hosting LLMs, private RAG, and air-gapped deployment. No spam.

Hardware Sizing Guide

Work the estimate the other way: start from a model class and size the hardware you need.

Model Registry

Sovereignty tiers, deployment runtimes, and a decision guide for private AI model selection.

Planning a real deployment?

Get a fixed-scope architecture review: model selection, hardware sizing, runtime topology, and a written findings document for your private RAG or air-gapped AI platform.

Book an architecture review

Estimates are approximate. Actual memory depends on runtime, batching, quantization format, KV cache implementation, and model architecture. Always benchmark before purchasing hardware.