Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Find the best local LLM for your hardware, ranked by benchmarks

github.com

Post reply on HN
Print view View original

41–50 of 80 posts

Re: Show HN: Find the best local LLM for your hardware, ranked by benchmarks

#41

Post by karmakaze »

entrope wrote: post #39
andyyyy64 wrote: post #21

Earlier quoted context omitted.

Fair question. llmfit answers "will this model fit in my memory?" — it's a fit/size calculator, and a good one. whichllm answers a different question: "of the models that fit, which is actually best?" It pulls candidates, then ranks them by merged real benchmarks (LiveBench / Artificial Analysis / Aider / Arena ELO / Open LLM Leaderboard) with a recency penalty, so a newer 27B beats an older 32B even though both fit…

Your LLM should have bothered to notice that llmfit also has quality scores (and defaults to sorting by them). One might quibble about weighting of factors -- llmfit favors Qwen3.6-35B-A3B over Qwen3.6-27B, whereas I found the quality of the latter to be worth waiting for -- but it absolutely ranks models by quality.

I thought that Qwen3.6-35B-A3B was notably missing from whichllm output too.

Re: Show HN: Find the best local LLM for your hardware, ranked by benchmarks

#43

Post by Aurornis »

1. The results of this tool are not good. It’s recommending outdated models like Qwen2.5 series and missing good new models.

2. This could have been a single web page that runs in your browser and lets you enter hardware specs, like all of the other tools like this. It is not a good idea to install and run unknown projects like this on your computer in this age.

3. The project is very obviously vibecoded, down to the README

4. Every comment from this account appears to be AI generated too.

I would recommend not installing and running this on your computer. There is no advantage over other tools and everything about the account and project looks like low effort AI generated content.

Re: Show HN: Find the best local LLM for your hardware, ranked by benchmarks

#45

Post by drzaiusx11 »

Where are the metrics being sourced from exactly? Externally? or does this project have benchmarks running somewhere for the purposes of this project. Latter would likely be more apples to apples comparisons in case some external sources are biasing etc

Re: Show HN: Find the best local LLM for your hardware, ranked by benchmarks

#46

Post by nullsanity »

schaefer wrote: post #32
jordiburgos wrote: post #10

This is very helpful too: https://www.canirun.ai/

> canirun.ai I run dgx spark, and the results here are soooo incomplete for my platform that I can’t trust this site (for my usecase).

[dead]

Re: Show HN: Find the best local LLM for your hardware, ranked by benchmarks

#48

Post by CharlesW »

Jeremy1026 wrote: post #44

canirun.ai does similar, but doesn't require any installs. I've found it to be pretty accurate for my setup too.

For me (64GB Apple Silicon), it recommended a year-old Llama model as "best for coding". That's a terrible first impression.

Re: Show HN: Find the best local LLM for your hardware, ranked by benchmarks

#50

Post by promptunit »

pornel wrote: post #8

It looks nice. I've been searching for something like this recently, and was frustrated with rankings that lack latest models or don't clearly distinguish quantizations. Showing quality loss per quantization is nice. I'd prefer this as a website, since I'd handle running of the model with a dedicated inference server anyway. It would be nice to see what's the maximum context length that can fit on top of the baseline…

[flagged]
Post reply on HN