Strata on a power limited 5090 and 96GB of DDR5-6400 is cranking out 150-200 tok/s decode and 5-6k prefill! Qwen3.8-Flash-Next at IQ3_S, CTX at 128k tokens (8-bit).

The AI race: China's open-weight models trail US closed models by just 7 months

Oct 14

Anthropic Executive Says Open-Source AI Models Are Higher Risk

Oct 14

ComfyUI v0.40.0 released

Oct 14

So this is how they do it --> RTX 5090, once a consumer gaming card, is now on smugglers’ menu alongside cigarettes

Oct 14