4 DGX Spark battle
Max thinking, 100% local. Qwen 3.8 Max (2.4T, 1bit): 53,448 tok, 1h 54m, 7.8 tok/s Ornith 1.5 (397B): 53,365 tok, 38m, 23.5 tok/s GLM 5.2: 20,864 tok, 12m, 29.6 tok/s 127k tokens of thinking on my desk, zero cloud. Which garden wins?
Qwen 3.8 27B 🚀vs Ornith-1.5-35B 🚀[4 Bit MLX]
Prompt: Bioluminescent Abyssal Temple (full prompt on the page) Harness: Grok Build Speed: Qwen - around 24tok/s, Ornith - around 55 tok/s Time to complete: Qwen - 33 minutes, Ornith - 16 minutes Results: Inspect yourself
Qwen 3.8 27B vs Ornith-1.5-35B 🔥
Gemini 3.7 Flash High vs Qwen 3.8 max vs Claude Opus 5 High vs GPT 5.6 sol xhigh
3D animated simulation of a Wankel Rotary Engine using Three js
You have reached the end of the archive
All of qwen38