Running 15 TurboQuant on Consumer GPUs — 100K Context on RTX 3090, 64K on RTX 4070 🚀 15 Extend LLM context to 100K tokens on consumer GPUs
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF Image-Text-to-Text • 27B • Updated Jul 9 • 23.9k • 616
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Text Generation • 67B • Updated about 1 hour ago • 1.32M • 429
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 Text Generation • 124B • Updated about 1 hour ago • 155k • 276
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled Image-Text-to-Text • 28B • Updated Jul 7 • 31.7k • • 2.94k
Running on CPU Upgrade 274 The Synthetic Data Playbook: Generating Trillions of the Finest Tokens 📝 274 Visualize synthetic‑data experiments as an interactive bookshelf