Creators
People who test open models, with the evidence behind their work
Alex Rivera@alexrunsRegular
Runs local models on real hardware and writes up what breaks.
23 works22 verified
Niko Laine@nodelordRegular
Big GPUs, small rooms. Tests whether a model is worth the electricity.
21 works21 verified
Samir Haddad@samir-localaiRegular
Builds offline assistants for clinics with no reliable internet.
21 works20 verified
Priya Raman@priya-infersRegular
Inference engineer. Writes about what quantization costs you.
20 works19 verified
Kwame Mensah@kwame-buildsRegular
Indie builder. Ships small tools that run models where the data lives.
20 works18 verified
Ivy Chen@polycount-ivyRegular
Builds evaluation suites for document AI. Messy receipts are my favourite benchmark.
19 works18 verified
Saoirse Byrne@saoirse-devRegular
Reviews local coding models on camera, with the runs to back them.
20 works17 verified
Li Wei@li-wei-evalsRegular
Chinese-language model reviews, run on my own machines first.
19 works16 verified
Jana Nováková@jana-novakRegular
PhD student. Reproduces other people's benchmark claims.
13 works13 verified
Ben Carter@ben-hardwareRegular
Hardware reviewer. Every GPU I review now gets a BenchClub run.
14 works12 verified
Omar Farouk@omar-quantRegular
Quantization nerd. AMD GPUs and CPUs welcome.
12 works12 verified
ghost_gpu@ghost-gpuRegular
Two used GPUs, one question: what's still worth running at home.
11 works11 verified
Arjun Mehta@arjun-shipsRegular
Makes LocalBench, a menu-bar app for your local models.
11 works10 verified
Emma Lindqvist@emma-testsRegular
Explains AI tools to people who just want them to work.
12 works10 verified
Fatima Zahra@fatima-codesMember
Writes about running models on modest hardware in North Africa.
9 works7 verified
Sofía Ruiz@sofia-agentsMember
Agent workflows that finish the job.
9 works7 verified
Mei Tanaka@mei-shipsMember
DevRel at Tern. I don't review Tern models.
8 works6 verified
Haruto Sato@tokyobenchMember
Small Macs, honest numbers.
7 works6 verified
Lucas Oliveira@lucas-oliveiraMember
IA local em português. Benchmarks before opinions.
6 works5 verified
Hana Kim@hana-kimMember
Korean-language agent tutorials.
4 works3 verified
Tom Becker@tom-edgeMember
Edge inference on CPUs and tiny boards.
3 works3 verified
Diego Hernández@diego-mxMember
Benchmarks for Spanish-speaking builders.
2 works2 verified
Ngozi Okafor@dr-okaforMember
Clinical NLP researcher. Tests whether small models can redact patient notes safely.
3 works2 verified
Yuki Watanabe@yuki-mlMember
Learning in public: one new model a week.
2 works1 verified