Running 11 TurboQuant on Consumer GPUs — 100K Context on RTX 3090, 64K on RTX 4070 🚀 11 Extend LLM context to 100K tokens on consumer GPUs
ibm-granite/granite-docling-258M Image-Text-to-Text • 0.3B • Updated Sep 23, 2025 • 174k • 1.19k
Qwen/Qwen3-Coder-30B-A3B-Instruct Text Generation • 31B • Updated Dec 3, 2025 • 1.35M • • 1.11k