Kingy AI
Explore
Work with Kingy
Menu
CALCULATED COMPARISON

Compare local runtime compatibility

Check Ollama and MLX LM against the same model and hardware settings. Unsupported combinations remain visible, and memory fit stays separate from measured speed.

Your setup: rtx-4090-24gb · 8,192 context tokens · 1 concurrent session. Change setup in the calculator →

CHANGE ONE DECISION

What if I change…

Compare the same model across alternatives. These are calculated memory results; runtime support is checked separately.

Qwen3 8B · chat · 1 concurrent session
AlternativeArtifactCalculated peakHeadroomMemory fit / runtimeTry it
OllamaChecks the exact binding for this hardware and artifact.Q8_09.9 GiB13.6 GiBcomfortableRuntime needs verificationOpen setup →
MLX LMApple Silicon only; unsupported combinations stay excluded.No supported artifact——No active, verified artifact and runtime binding matches this setup.Open setup →

No compatible artifact means unknown here, not that the model can never run. Multiple GPUs, multi-Spark clusters and hybrid offload need a topology-specific calculation.

Same calculator, exact files

Every row uses the planner’s reviewed model, artifact and runtime records. A missing artifact is shown as unsupported rather than estimated from parameter count. Higher precision does not prove better task quality; a runtime compatibility record does not establish speed.

llama.cpp, vLLM, multi-device inference and hybrid offload are not calculated in this surface. No cross-runtime speed scores are mixed.

Kingy AI Local Lab

Evidence first. Estimates labelled. Corrections preserved.

JSONCSVMethodologyMore Kingy tools