Liquid AI releases a 230M model optimized for phones, Raspberry Pi, and robots
mpfect
17 points
1 comment
July 01, 2026
Related Discussions
Found 5 related stories in 1217.5ms across 14,015 title embeddings via pgvector HNSW
- Liquid AI reveals 8B-A1B MoE trained on 38T simjnd · 171 pts · May 29, 2026 · 67% similar
- LM Studio Bionic: the AI agent for open models minimaxir · 204 pts · July 16, 2026 · 57% similar
- OpenAI and Broadcom unveil LLM-optimized inference chip meetpateltech · 141 pts · June 24, 2026 · 56% similar
- Running local models on an M4 with 24GB memory shintoist · 225 pts · May 10, 2026 · 55% similar
- Mesh LLM: distributed AI computing on iroh tionis · 176 pts · July 11, 2026 · 53% similar
Discussion Highlights (1 comments)
potus_kushner
these LFM 2.5 models are crazy fast. the (biggest in series) 8B-A1B model produces 35-40 t/s on an aged 6-core CPU using llama.cpp. it's my go-to model for whenever i need fast local inference. it's also pretty good at toolcalling. would love to see more finetunes on HF, but it appears not many people discovered it yet.