Free · no sign-up · data verified weekly

Which local LLM should you run on your hardware?

Pick your GPU, Mac or RAM. Get models that fit (weights + KV cache), a speed figure labelled measured, scaled or estimated, and a copy-paste command for llama.cpp or Ollama.

VRAM fit mathMoE offload flagsReal benchmarksOpen data

Sponsor slot. No sponsor yet and no link.

Sort & filter

Sort by

Order

Search Speed source Fit License Model family Min tokens/sec: any

Affiliate box: cloud GPU rental. No links yet.

How these numbers are made

Fit

GGUF file size (read from Hugging Face) + KV cache (computed from each model's config; sliding-window and linear-attention layers handled) + ~1 GB overhead per GPU.

Speed

Memory bandwidth × efficiency ÷ bytes read per token. Efficiency is calibrated against real runs. Real results vary with backend, drivers and context.

Long context

Each model is capped at its verified maximum context. Beyond it, only models whose card documents YaRN are offered, flagged extended. Speed at depth and time-to-first-token are always estimates (penalty fitted to measured runs up to 128k; beyond that it is extrapolated). Long context needs flash attention and lots of memory.

Badges

measured median of real runs.
scaled from measured a same-size or same-model-other-quant run, scaled by bytes read.
estimated bandwidth formula, not a benchmark.

Ranking

Fits and is fast enough first, then bigger. A heuristic, not a quality benchmark. Assumptions are listed in hardware.json.

Browse by hardware, memory or model

The advisor above is interactive; these pages list the same numbers as plain, linkable tables.

Data changelog

Hardware pages: all configs · Submit your benchmark · Data sources & attribution

Which local LLM should you run on your hardware?

Sort & filter

How these numbers are made

Fit

Speed

Long context

Badges

Ranking

Browse by hardware, memory or model

Hardware

By memory

Models

Data

Data changelog