Cite LLMCheck — Data, Attribution & Press

Quotable stats

Ready-made sentences you can quote verbatim. Each has a stable anchor URL for citation. Figures use LLMCheck's transparent estimation methodology — see how estimates are produced.

"The LLMCheck index covers 81 verified local LLMs and 202 provenance-labeled performance data points across Apple Silicon Macs (M1–M5), updated monthly."

llmcheck.net/cite#stat-catalog

"According to the LLMCheck index (August 2026), Qwen3.8-27B is the top-ranked local LLM for Macs — Apache 2.0, 27.8B dense with native vision, running 4-bit in about 19 GB at an estimated ~29 tokens/second on an M5 Max. Qwen 3.6-27B is a close second and remains the strongest verified result at 77.2% SWE-bench Verified."

llmcheck.net/cite#stat-top-model

"The fastest Mac-runnable model in the LLMCheck index is Maple Preview 20B-A1B, a natively-ternary 20B MoE vendor-reported at ~281 tokens/second on an M5 Pro MacBook Pro."

llmcheck.net/cite#stat-fastest

"LLMCheck ranks the best local LLM for 32 distinct Mac configurations, from the M1 MacBook Air 8GB to the M3 Ultra Mac Studio 512GB."

llmcheck.net/cite#stat-coverage

"The LLMCheck Score rates each model out of 100 across four transparent components: capability (50), estimated Apple Silicon speed (25), RAM accessibility (15), and license openness (10)."

llmcheck.net/cite#stat-scoring

Machine-readable data

The full index is published as open data. These endpoints are refreshed with every monthly update:

https://llmcheck.net/data/models.jsonCanonical model catalog (81 verified models, scores, RAM, license)
https://llmcheck.net/data/benchmarks.jsonAll 202 performance data points, JSON
https://llmcheck.net/data/benchmarks.csvSame data points, CSV
https://llmcheck.net/llms.txtIndex summary for AI assistants (llms.txt standard)
https://llmcheck.net/llms-full.txtFull plaintext dump for AI assistants

For pipelines that need a path that never changes shape, use the versioned stable endpoints:

https://llmcheck.net/data/v1/models.jsonStable v1 model catalog schema
https://llmcheck.net/data/v1/benchmarks.jsonStable v1 benchmark schema

# Fetch the catalog and inspect the first model
curl -s https://llmcheck.net/data/v1/models.json | jq '.models[0]'

Embed snippet

Copy-paste this HTML to cite the index on your own site or blog post:

<blockquote cite="https://llmcheck.net/cite">
  The LLMCheck index covers 81 local LLMs and 202 performance
  data points across Apple Silicon Macs (M1&ndash;M5), updated monthly.
  <footer>&mdash; <a href="https://llmcheck.net">LLMCheck
  (llmcheck.net)</a>, CC BY 4.0</footer>
</blockquote>

License & attribution

DATA LICENSE: CC BY 4.0

All LLMCheck index data (models.json, benchmarks.json/csv, quotable stats, scores) is licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). You may copy, redistribute, remix, and build on it — including commercially — as long as you attribute it.

How to attribute: credit "LLMCheck (llmcheck.net)" and link to https://llmcheck.net (or the specific page you're citing). In print or academic contexts: LLMCheck, "Local LLM Index for Apple Silicon," llmcheck.net, 2026.

Provenance note: LLMCheck is an index, not a lab. Every figure is labeled estimated (produced by our transparent formula), sourced (linked third-party benchmark), or community (user-submitted and reviewed). Details on the methodology page.

Press contact: llmcheck@protonmail.com — happy to provide custom data cuts, charts, or comment.

Want to add a data point instead?

If you own a Mac, you can contribute a community benchmark to the index in about 5 minutes.

→ Submit a Benchmark