Liquid AI ships open d1 decision models; 3B on RTX 3090 beats OpenAI API 8ms vs 345ms
philipvollet · x · 2026-10-08
Liquid AI released Open d1, an open-weight decision-model family: d1-3B (text+vision) and d1-omni-600M (text+image or text+audio), built for real-time decision-making from DGX data centers down to RTX workstations and edge Jetson devices. A demo shows local d1-3B on a single RTX 3090 deciding in 8ms — its Snake ran 82 moves/sec and ate 86 apples, while OpenAI's API at 345ms per call managed 3. The reposter Atomic Chat uses it to plug its local inference client.
More from Infra
- Chrome's new DecisionModel API reverse-engineered: prompts, limits and engine tests — dejanseo · 2026-10-08
- China's Power Glut Meets Data Centers; Immersion Cooling Traced to Bitcoin Miners — teortaxesTex · 2026-10-08
- omarchy-cluster runs the full 753B-param GLM-5.3 across four old Macs as one endpoint — natesiggard · 2026-10-08
- Only Samsung HBM meets Nvidia Vera Rubin performance requirements, per leak — zephyr_z9 · 2026-10-08
- Box CEO on agent compute: one app serving 100M users would need $2.8B in infra — inductionheads · 2026-10-08
- Firmus, valued near $44bn, may shelve ASX IPO as investors balk — nordicinst · 2026-10-08