view reply model seems pretty aight for its size definitely benchmaxxed though, but the real issue is the horrendous output speed
DavidAU/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL Text Generation ⢠42B ⢠Updated Oct 28, 2025 ⢠3
TeichAI/deepseek-v3.2-speciale-OpenCodeReasoning-3k Viewer ⢠Updated Dec 7, 2025 ⢠2.95k ⢠184 ⢠6