Community poll of 793 MLX users: oMLX wins at 55.5%, dominating Ultra chips
HankYeomans · x · 2026-10-03
The MLX Engines 2026 community poll (793 voters, 23 engines) is out. oMLX tops the ranking at 55.5%, followed by MLX-Serve (38.2%), LM Studio (31.9%), and MTPLX (26.0%).
Key breakdowns:
- By chip: LM Studio leads on base M chips, while oMLX hits 71% on Ultra variants
- By memory: three in four voters with 256 GB+ unified memory use oMLX
- Audience: the 489 chip respondents are mostly M5 Max + 128 GB setups
- Most voters picked multiple engines; turnout peaked in the first 24 hours
Full report at poll.devocracy.it.
More from Infra
- Open-source Strata runs a 125B-param Qwen model on a 12GB consumer GPU — lxfater · 2026-10-03
- Chip design is a ~10^2,632,341 search problem — AI and agents are turning hardware into search — ai · 2026-10-03
- Redis Creator antirez Ships DwarfStar 4, an MIT-Licensed Local Inference Engine — petrusenko_max · 2026-10-03
- The $899 Mac Mini M6 was built for 24/7 agentic computing — most owners use it to check email — hey_abusiddik · 2026-10-03
- Modal VM Sandboxes hit GA: demo runs Docker Compose apps, tests and coding agents — charles_irl · 2026-10-03
- Local AI user asks: why does everyone enjoy taming the beast of complexity? — kathi7 · 2026-10-03