cd/entity/Cactus Compute· home› entities› Cactus Compute
grep -l @cactus compute /news/*.json | wc -l → 2

Cactus Compute

mentions 2 type Person feed RSS

// recent coverage 2 mentions

21:29
2026-08-10
promptcube3.com
artificial-intelligence

Needle 2 fits a functional LLM into just 14MB

Cactus Compute's Needle 2 model fits a functional LLM into just 14MB, using Simple Attention Networks to reduce per-token computation to 70 MFLOPs, compared to 164 MFLOPs for a standard transformer of…

21:19
2026-08-10
runtimewire.com
artificial-intelligence

Cactus ships 14MB Needle 2 for tool calling on cheap devices

Cactus Compute, a Y Combinator Summer 2025 startup, released Needle 2, a 14MB language model for tool calling on low-memory devices, capable of running on phones, wearables, home devices, robots, and …

// co-occurs with top 8 entities
Needle 2 2 LFM2.5 1 Apple 1 DeepSeek 1 Henry Ndubuaku 1 Roman Shemet 1 Y Combinator 1 Pebble 1
// topics top 6 topics
artificial intelligence 2 large language models 2 machine learning 1 ai agents 1 ai products 1 ai infrastructure 1