Running 8 TurboQuant on Consumer GPUs — 100K Context on RTX 3090, 64K on RTX 4070 🚀 8 Extend LLM context to 100K tokens on consumer GPUs
cloudbjorn/Qwen3.6-35B-A3B_Opus-4.6-Reasoning-3300x-GGUF Text Generation • 35B • Updated 24 days ago • 428 • 1