canirun.ai
Ranked 2 of 4 model fit calculators by recommenders
Lets you pick your hardware and see which local AI models run on it, with no install needed. Critics say results are often inaccurate or incomplete.
Lets you pick your hardware and see which local AI models run on it, with no install needed. Critics say results are often inaccurate or incomplete.
19 people gave an opinion
- recommend it
- 12
- criticize it
- 7
- approval share
- 63%
Recommended in 7 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 12 people recommend itNeeds 10 or more, met.
- 1.7 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 7 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Accurate for the user's own setup
“I do appreciate that the "canirun" one was also wrong but let me pick my real card from the dropdown with results that seemed much more accurate.”
Comment from 21 Jul 2026 in “I built a page that tells you what AI model your laptop can run” “doesn't require any installs. I've found it to be pretty accurate for my setup too.”
Comment from 15 May 2026 in “Show HN: Find the best local LLM for your hardware, ranked by benchmarks” “I find this to be pretty accurate”
Comment from 21 Jul 2026 in “I built a page that tells you what AI model your laptop can run” Matches models to chosen hardware specs
“toggle your computer specs at the top for a refined list of models and tokens/sec”
Comment from 10 Aug 2026 in “Meta Muse Glimmer – open weights 30B local coding model” “can help you find a model that'll run on your hardware”
Comment from 17 Apr 2026 in “Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B?” “visit canirun.ai to find a suitable model”
Comment from 17 Sep 2026 in “Intelligence per Watt: Measuring Intelligence Efficiency of Local AI” Helps decide which model to run
“can help you find a model that'll run on your hardware”
Comment from 17 Apr 2026 in “Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B?” “That may help make the decision.”
Comment from 30 Mar 2026 in “Ask HN: M5 MacBook Pro buyers, worth spending the $$$ to maybe run LLMs local?” “might answer that question”
Comment from 13 Jun 2026 in “AI Coding at Home Without Going Broke”
What people warn about
Each mark is one comment
Ignores quantizations and MoE models
“That site doesn't seem to consider the quants.”
Comment from 13 Jun 2026 in “AI Coding at Home Without Going Broke” “canirun doesn't work well for MoE models”
Comment from 17 May 2026 in “Show HN: Find the best local LLM for your hardware, ranked by benchmarks” Estimates often wrong or far off
“I do appreciate that the "canirun" one was also wrong but let me pick my real card from the dropdown with results that seemed much more accurate.”
Comment from 21 Jul 2026 in “I built a page that tells you what AI model your laptop can run” “The estimates seems far off as well”
Comment from 15 May 2026 in “Show HN: Find the best local LLM for your hardware, ranked by benchmarks”
Other model fit calculators people recommend
The three most recommended other model fit calculators, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| llmfit | 20 | 2 | 91% | 6 | — | Approved |
| canirun.aiThis page | 12 | 7 | 63% | 7 | — | — |
| Llmspeed | 8 | 9 | 47% | 1 | — | — |
| LLM model right-sizing tool | 5 | 2 | 71% | 1 | — | — |
What people said
16 of the 19 comments that mention it, newest first. Each links to the original comment.
“visit canirun.ai to find a suitable model”
“toggle your computer specs at the top for a refined list of models and tokens/sec”
“it is very dangerous to your wallet”
“I do appreciate that the "canirun" one was also wrong but let me pick my real card from the dropdown with results that seemed much more accurate.”
“I find this to be pretty accurate”
“That site doesn't seem to consider the quants.”
“might answer that question”
“canirun doesn't work well for MoE models”
“doesn't require any installs. I've found it to be pretty accurate for my setup too.”
“the results here are soooo incomplete for my platform”
“Every browser gives me a different result, I guess I can't blame the site for that.”
“The estimates seems far off as well”
“look how long its been since it's been updated”
“Check out https://www.canirun.ai/”
“can help you find a model that'll run on your hardware”
“That may help make the decision.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.