VQV Signal

OPEN SOURCE WATCH TECHNICAL

FreeToken runs very large open MoE models on a single consumer GPU (secondhand)

AIGCLINK reports that researchers from Berkeley, MIT and others released FreeToken, an open-source inference engine that it says ran DeepSeek 284B at 22–25 tokens per second on an RTX 5090. It says decode throughput was 1.3–2.1x faster than existing local...

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-15T05:35:00+00:00 Detected 2026-11-15T18:19:37+00:00
View original source

AIGCLINK reports that researchers from Berkeley, MIT and others released FreeToken, an open-source inference engine that it says ran DeepSeek 284B at 22–25 tokens per second on an RTX 5090. It says decode throughput was 1.3–2.1x faster than existing local...

AIGCLINK reports that researchers from Berkeley, MIT and others released FreeToken, an open-source inference engine that it says ran DeepSeek 284B at 22–25 tokens per second on an RTX 5090. It says decode throughput was 1.3–2.1x faster than existing local engines and that it can serve as the backend for coding...

Signal Strength 95% Technical label WATCH Public Interest 49 Category OPEN SOURCE 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 26 Novelty Interest Score 94 Consequence Score 30 Curiosity Score 16 Shareability Score 61

VQV surfaced this signal because it is recent, relevant to AI Coding Tools, connected to Scobleizer News Pulse (X).