Edge0 open-sources 145B and 120B on-device models
Understand this story
Edge0 has open-sourced two on-device models, Edge0-145B and Edge0-120B, and simultaneously released a unified inference framework and deployment tools. According to its introduction, the core model capabilities can run offline, require no account, and have no usage quota limits. Edge0 says the 145B model can run locally on compatible laptops, reporting peak memory of 29GB, decoding speed of 80+ tokens/s, prefill of 1100+ tokens/s, and support for 128K–256K context; on day one it supports macOS, Windows, and Linux, covering Apple M-series chips and NVIDIA platforms such as RTX Spark, RTX 4090, and RTX 5090. However, devices with very low compute power currently cannot run the 145B model locally.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIFeaturedEdge0-145B: Frontier AI Capabilities on Your Own Computer
The company open-sourced Edge0-145B and Edge0-120B, describing Edge0-145B as the first open-source 145-billion-parameter on-device model, alongside a unified inference framework and deployment tools. It reports 29GB peak memory, 80+ tokens/s decoding, 1,100+ tokens/s prefill, roughly 120W typical power and 128K–256K context on a compatible laptop, with benchmark scores compared against named cloud models. The release also describes shared-matrix sparse experts, tiered GPU/system-memory/SSD loading and CPU-GPU co-scheduling, plus local demonstrations in video, Blender 3D scenes, games, drone control and PCB design.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 13 08:00
- Change in the past 24 hours
- -51%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.