Running 14 TurboQuant on Consumer GPUs — 100K Context on RTX 3090, 64K on RTX 4070 🚀 14 Extend LLM context to 100K tokens on consumer GPUs
mradermacher/DeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner-GGUF 16B • Updated Jul 31, 2025 • 897 • 13
mradermacher/DeepSeek-R1-Distill-Qwen-14B-Uncensored-Reasoner-i1-GGUF 15B • Updated Feb 7, 2025 • 769 • 6
mradermacher/DeepSeek-R1-Distill-Qwen-7B-Uncensored-Reasoner-i1-GGUF 8B • Updated Jan 23, 2025 • 291 • 8