Edge0 releases 145B open model built to run on one consumer GPU

Nov 13, 2026
The sparse mixture-of-experts model is derived from Qwen3.8-Flash-Next; Edge0 reports its own speed and benchmark figures.

Edge0 has released Edge0-145B and Edge0-120B, open-weight sparse mixture-of-experts models built to run on a single consumer NVIDIA GPU, according to the model card on Hugging Face. The models are derived from Qwen3.8-Flash-Next and use 512 experts with 10 active per token, a 256,000-token context and native 4-bit training.

Edge0 reports 121.2 tokens per second for agent decoding and a score of 86.5 on Terminal-Bench 2.1 for the 145B model in its Q3_K format on an RTX 5090 D with 24 GB of memory. The figures are Edge0's own measurements. The models use Edge0's own community licence on top of Qwen's licence, which allows research, internal use and commercial use of outputs but not selling the model or running it as a commercial service without separate permission.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Guide
Biggest AI compute deals

Biggest AI compute deals

The largest announced contracts to buy chips or cloud capacity for AI

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.