Gradient(@Gradient_HQ):We also tested the messier setups. Using Parallax, we trained Qwen3-8B on distributed RTX 5090s. 36% cheaper than centralized A100s, same scores, zero divergence. We even trained a 0.6B agent to beat LLMs at No-Limit Texas Hold'em. Reliable results with unreliable compute.

Gradient

@Gradient_HQ

Open infrastructure for open intelligence. Lattica · Parallax · Echo

加入 May 2024

76 正在关注 705.9K 粉丝

Gradient@Gradient_HQ

2026.02.12 14:08

We also tested the messier setups. Using Parallax, we trained Qwen3-8B on distributed RTX 5090s. 36% cheaper than centralized A100s, same scores, zero divergence. We even trained a 0.6B agent to beat LLMs at No-Limit Texas Hold'em. Reliable results with unreliable compute.

显示更多