How Can I Run AI works

What the checker answers

Can I Run AI estimates whether a local AI model fits on a selected GPU or Apple Silicon device, the likely generation-speed range, a safe context length, and the most practical runtime. It is a planning tool: use it before downloading a large model, then confirm with the runtime on your own machine.

V1 currently displays text-generation models. The catalog structure is designed to support embedding, reranking, speech, transcription, image, and video models later, but those categories are not shown until their estimates are useful enough.

Hardware detection and selection

On first visit, the browser tries WebGPU adapter information and then a WebGL renderer string. Browser privacy controls often reduce or hide these details. navigator.deviceMemory, when available, is only a coarse system-memory hint.

Detection runs locally. The raw adapter or renderer label is displayed only so you can verify it; it is not included in a share snapshot. You can select a known profile or enter custom accelerator memory, system memory, and bandwidth at any time. The confirmed profile—not a hidden fingerprint—is what drives the estimate.

The catalog contains desktop and laptop NVIDIA RTX generations, Apple Silicon memory variants, experimental AMD and Intel profiles, and a CPU fallback. Laptop GPUs with the same product family can vary by power limit, so their speed ranges are intentionally wider.

Memory estimate

Every result adds three components:

1. Model weights — parameter count × effective quantization bits, plus a small file/runtime allowance.
2. KV cache — model-family estimate × selected context length. Longer context increases this component.
3. Runtime overhead — buffers, temporary allocations, and runtime bookkeeping.

Usable accelerator memory is lower than the advertised total because the operating system, display, and runtime also need memory. Apple Silicon uses unified memory, so the estimate reserves a larger system allowance.

The four fit labels mean:

• Runs comfortably — the estimate fits with at least 20% accelerator-memory headroom.
• Tight fit — it fits, but background GPU use or longer prompts can cause allocation failures.
• Runs with offload — some weights can move to system memory, usually with a substantial speed penalty.
• Won't fit — the estimate exceeds practical accelerator plus system-memory capacity.

Quantization and precision

The checker lists Q4_K_M, Q5_K_M, Q8_0, BF16, FP8, and NVFP4. Q4 is usually the best starting point for limited memory. Q5 uses more memory in exchange for better quality retention. Q8 is close to the original weights. BF16 represents the original 16-bit weights and can be useful on very large-memory machines. FP8 requires supported NVIDIA Ada, Hopper, or Blackwell hardware. NVFP4 requires NVIDIA Blackwell hardware.

All choices remain visible. Unsupported hardware-specific formats are disabled with a reason instead of being hidden. Memory capacity alone does not make a GPU support FP8 or NVFP4: the required compute architecture and runtime kernels must also exist. File formats and kernels vary between runtimes, so the numbers are normalized planning estimates, not a promise that every repository exposes every precision artifact.

Speed estimate and runtime

Speed is a range, not a benchmark. It combines approximate memory bandwidth, accelerator class, model size, active parameters for mixture-of-experts models, and an offload penalty. Prompt processing and token generation are different workloads; the displayed range primarily represents interactive token generation after the prompt is processed.

The runtime recommendation is selected from the precision and hardware combination. Apple Silicon prefers MLX; GGUF profiles use Ollama or llama.cpp; native BF16/FP8/NVFP4 estimates use Transformers, vLLM, or TensorRT-LLM as appropriate. Driver versions, kernel support, thermals, power limits, and concurrent workloads can move real performance outside the estimate.

Arena quality ranking

When an exact model-version match exists, the list also shows its open-source rank, score, and vote count from the public Arena Text Leaderboard dataset. Arena measures anonymous human preference, not local speed. Unmatched or ambiguous versions stay unranked rather than inheriting a nearby model's score.

The snapshot currently uses Arena data published on 2026-07-10. The dataset is released under CC BY 4.0; the UI links to the filtered Arena leaderboard and identifies the publication date.

Catalog evidence

Each model records its source URL, retrieval date, and confidence. Sources favor official model cards and publisher repositories. Parameter counts, context limits, licenses, and commercial-use terms are catalog facts. Memory and speed are calculated estimates, and the detail view keeps those two kinds of information visibly separate.

Catalog and evaluation-engine versions appear with every result. Shared pages freeze the inputs, results, model identity, and evidence metadata from the time the link was created; they are not recalculated when the live catalog changes.

Interpreting a result safely

Leave extra memory for the desktop, browser, and other applications. Start with the recommended Q4 model and a shorter context, close GPU-heavy applications, and test a representative prompt. For business use, follow the linked model license and verify its current terms with the model publisher.

This tool does not execute third-party models, inspect files on your computer, or guarantee model quality, accuracy, safety, or legal suitability.