VQV Signal

ROBOTS & HARDWARE WATCH TECHNICAL

ModelScope hosts Edge0-145B, a sparse agent model built to run on one consumer GPU

ModelScope highlighted Edge0-145B, a latent mixture-of-experts model that activates 10.12B of its parameters per token across 512 experts, with 256K context. Edge0 reports 86.5 on T...

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-16T05:40:00+00:00 Detected 2026-11-16T18:24:30+00:00
View original source

ModelScope highlighted Edge0-145B, a latent mixture-of-experts model that activates 10.12B of its parameters per token across 512 experts, with 256K context. Edge0 reports 86.5 on T...

ModelScope highlighted Edge0-145B, a latent mixture-of-experts model that activates 10.12B of its parameters per token across 512 experts, with 256K context. Edge0 reports 86.5 on Terminal-Bench 2.1 and 64.6 on DeepSWE 1.1, and 121.2 tokens per second of agent decoding for its Q3_K build on an RTX 5090 D 24GB; a...

Hardware and robotics watchers may want to track whether this becomes a product, benchmark, or deployment signal.

Signal Strength 90% Technical label WATCH Public Interest 42 Category ROBOTS & HARDWARE Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 51 Practical Impact Score 28 Novelty Interest Score 70 Consequence Score 18 Curiosity Score 16 Shareability Score 57

VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Scobleizer News Pulse (X).