PulseAugur
EN
LIVE 14:31:01

Jailbroken PS4 runs 9B parameter AI model offline

A jailbroken PlayStation 4 can now run a 9-billion-parameter AI model, Qwen3.5-9B, offline thanks to the open-source Garlic LLM project. This allows the console's 2013-era GPU to directly process the model, which has been optimized to fit within the console's 8GB of memory using 4-bit and 3-bit weights. The system can achieve speeds of up to 43 tokens per second for text generation and also supports voice conversation and dictation. AI

IMPACT Demonstrates the potential for running sophisticated AI models on older, consumer-grade hardware, potentially expanding access.

RANK_REASON This is a third-party project using a consumer device to run an AI model, not a direct release from a frontier lab.

Read on Tom's Hardware →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Jailbroken PS4 runs 9B parameter AI model offline

How we ranked this

Signal score
37 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This is a third-party project using a consumer device to run an AI model, not a direct release from a frontier lab.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Tom's Hardware TIER_1 English(EN) · Shane Downing ·

    Jailbroken PS4 runs 9-billion-parameter AI model at up to 43 tokens per second

    Garlic LLM runs Alibaba’s Qwen3.5-9B on a jailbroken PlayStation 4’s GPU, fully offline, at 31 to 39 tokens per second.