Unverified50% confidenceFactExact time
A jailbroken PlayStation 5 can run local large language models at over 100 tokens/s.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedDuring the jailbreak, by reallocating CPU priority, unlocking general-purpose GPU compute access, freeing additional memory bandwidth, and combining with a model fork (PS5LM) optimized for parallel processing and memory bandwidth, an inference speed of 100+ tokens/s is achieved.64% similarUnverifiedUnder this configuration, the 35B model achieves a measured single-user peak speed of approximately 80 tokens/second, with concurrent throughput exceeding 500 tokens/second.62% similarUnverifiedNaive-N0.5-Flash can be optimized to approximately 2000 tokens/s in single-concurrency scenarios, and can exceed 50 tokens per second in multi-concurrency scenarios60% similarUnverifiedThe Gemma open-source model achieved 2.85x end-to-end inference acceleration on A100 via vLLM, with throughput increasing from about 37,900 tokens/second to over 108,000 tokens/second, while maintaining 100% token consistency and zero quality degradation.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053963API
curl https://kongchang.com/api/v1/knowledge/claims/1053963MCP
get_claim(id=1053963)