Edge0 open-sources 145B and 120B on-device models
Start here
Edge0 has open-sourced its Edge0-145B and Edge0-120B models, together with a unified inference framework and deployment tools, and says Edge0-145B is the first open-source 145B-parameter model that runs on-device. The company reports that on a compatible laptop the 145B model needs 29GB peak memory, prefills at over 1,100 tokens/s, decodes at over 80 tokens/s and draws roughly 120W, with 128K–256K context. Edge0 says the core capabilities work offline, without an account or usage quota, and that day-one support covers macOS, Windows and Linux, including Apple M-series chips and NVIDIA RTX Spark, RTX 4090 and RTX 5090. Edge0 cites internal scores of 64.6 on DeepSWE 1.1, 86.52 on Terminal-Bench 2.1, 90.4 on GPQA-Diamond and 80.6 on IFBench, and says the weights are on Hugging Face. The company also says a very low-compute device cannot currently run the 145B model locally.
Generated from reports · updated 2 d ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIPicksEdge0 open-sources Edge0-145B and Edge0-120B on-device models with inference framework
Edge0 open-sourced Edge0-145B and Edge0-120B along with its unified inference framework and deployment tools, claiming Edge0-145B is the first open-source 145B-parameter on-device model. The company reports 29GB peak memory, 1,100+ tokens/s prefill, 80+ tokens/s decode and roughly 120W typical power on a compatible laptop, with 128K–256K context. It cites internal scores of 64.6 on DeepSWE 1.1, 86.52 on Terminal-Bench 2.1, 90.4 on GPQA-Diamond and 80.6 on IFBench, and says weights are on Hugging Face with day-one support for macOS, Windows and Linux.
Heat for this event
Not enough continuous observations yet to draw a trend.