Hacker ApprovedDepartments

llmfit

Hacker Approved

The most recommended of 4 model fit calculators

Terminal tool that detects your hardware and shows which local AI models will run on it, and at what speeds. Some find its model suggestions outdated.

Terminal tool that detects your hardware and shows which local AI models will run on it, and at what speeds. Some find its model suggestions outdated.

22 people gave an opinion

recommend it
20
criticize it
2
approval share
91%
Each figure is one person. RecommendsCriticizes

Recommended in 6 of 13 months

  1. November 2025: not recommended
  2. December 2025: not recommended
  3. January 2026: not recommended
  4. February 2026: not recommended
  5. March 2026: recommended
  6. April 2026: recommended
  7. May 2026: recommended
  8. June 2026: not recommended
  9. July 2026: recommended
  10. August 2026: recommended
  11. September 2026: recommended
  12. October 2026: not recommended
  13. November 2026: not recommended (month in progress)

Why it carries the badge

  • 20 people recommend itNeeds 10 or more, met.
  • 10 recommenders for every criticNeeds 2 to 1 or better, met.
  • Recommended in 6 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

  • Detects hardware and shows compatible models

    “runs in your terminal and nicely filters out models compatible with your machine”

    Comment from 6 Aug 2026 in “What's My Local AI?”

    “It accurately got my GPU and specs without asking for any permissions.”

    Comment from 13 Mar 2026 in “Can I Run AI locally?”

    “It shows you exactly what models you can run and at what speeds”

    Comment from 21 Jul 2026 in “I built a page that tells you what AI model your laptop can run”
  • Accurate fit and speed estimates

    “It shows you exactly what models you can run and at what speeds”

    Comment from 21 Jul 2026 in “I built a page that tells you what AI model your laptop can run”

    “it's a fit/size calculator, and a good one”

    Comment from 15 May 2026 in “Show HN: Find the best local LLM for your hardware, ranked by benchmarks”

    “I've found it reasonably accurate.”

    Comment from 21 Mar 2026 in “Tinybox- offline AI device 120B parameters”
  • Recommended as a useful tool

    “I love the llmfit project for seeing what will run on your hardware”

    Comment from 18 May 2026 in “Qwen 3.7 Preview”

    “That's super handy, thanks for sharing the link.”

    Comment from 13 Mar 2026 in “Can I Run AI locally?”

    “llmfit is your friend here”

    Comment from 29 Sep 2026 in “GLM-5.3 and the spread of advanced cyber capabilities”

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.

llmfit compared with 3 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
llmfitThis page20291%6—Approved
canirun.ai12763%7——
Llmspeed8947%1——
LLM model right-sizing tool5271%1——
See all 4 model fit calculators, ranked

What people said

20 of the 25 comments that mention it, newest first. Each links to the original comment.

“llmfit is your friend here”

RecommendsComment from 29 Sep 2026 in “GLM-5.3 and the spread of advanced cyber capabilities”

“runs in your terminal and nicely filters out models compatible with your machine”

RecommendsComment from 6 Aug 2026 in “What's My Local AI?”

“It shows you exactly what models you can run and at what speeds”

RecommendsComment from 21 Jul 2026 in “I built a page that tells you what AI model your laptop can run”

“After being annoyed by llmfit”

CriticizesComment from 4 Jun 2026 in “Show HN: Will It Fit? – Opinionated Normal People Llama.cpp VRAM Estimator”

“it's a terrible experience lacking any sort of intent or reason”

CriticizesComment from 4 Jun 2026 in “Gemma 4 12B: A unified, encoder-free multimodal model”

“I love the llmfit project for seeing what will run on your hardware”

RecommendsComment from 18 May 2026 in “Qwen 3.7 Preview”

“It would organize it per use and selection was solid.”

RecommendsComment from 15 May 2026 in “Show HN: Find the best local LLM for your hardware, ranked by benchmarks”

“llmfit also has quality scores (and defaults to sorting by them)”

MixedComment from 15 May 2026 in “Show HN: Find the best local LLM for your hardware, ranked by benchmarks”

“it's a fit/size calculator, and a good one”

RecommendsComment from 15 May 2026 in “Show HN: Find the best local LLM for your hardware, ranked by benchmarks”

“gives a good approximation of that”

RecommendsComment from 22 Apr 2026 in “Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model”

“These might help if the provider doesn't offer the same details themselves.”

RecommendsComment from 22 Apr 2026 in “Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model”

“I've found it reasonably accurate.”

RecommendsComment from 21 Mar 2026 in “Tinybox- offline AI device 120B parameters”

“you can get LLMFit to recommend hardware requirements with llmfit plan --context”

RecommendsComment from 14 Mar 2026 in “Can I Run AI locally?”

“I feel like they both solve different issues well”

RecommendsComment from 13 Mar 2026 in “Can I Run AI locally?”

“it's buried behind relatively obsolete suggestions like the Qwen 2.5 series”

MixedComment from 13 Mar 2026 in “Can I Run AI locally?”

“That would be a great tool to integrate with ollama.”

RecommendsComment from 13 Mar 2026 in “Can I Run AI locally?”

“That's super handy, thanks for sharing the link.”

RecommendsComment from 13 Mar 2026 in “Can I Run AI locally?”

“It accurately got my GPU and specs without asking for any permissions.”

MixedComment from 13 Mar 2026 in “Can I Run AI locally?”

“llmfit is far more useful as it detects your system resources”

RecommendsComment from 13 Mar 2026 in “Can I Run AI locally?”

“Way less intrusive than installing this thing”

CriticizesComment from 2 Mar 2026 in “Right-sizes LLM models to your system's RAM, CPU, and GPU”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.