models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Jack-3.8-27B-Coder-16GB-VRAMQwen3.6-35B-A3B-vram13-GGUFQwen3.8-2B-Distill-GGUFQwopus3.6-35B-A3B-Coder-vram13-GGUFGemma-4-26B-A4B-it-vram14-iq4xs-imatMiqu-1-70b-24GB-VRAM-IQ2-XS-SOTAspr-qwen3_5-9b-dora-vramsafe-ggufQwen3.6-27B-vram14-GGUFQwen3-0.6B-GGUF-for-24GB-VRAMgranite-q4kmKleiner-Coder-35B-vram13-MTPDictaLM-3.0-24B-Thinking-FP8-Q8_0-GGUFDictaLM-3.0-24B-Thinking-FP8-Q4_0-GGUFDictaLM-3.0-24B-Thinking-W4A16-Q4_K_M-GGUFDictaLM-3.0-24B-Base-W4A16-Q4_0-GGUFMeta-Llama-3-8B-Instruct-Q6_K-GGUFDictaLM-3.0-24B-Thinking-FP8-Q4_K_M-GGUFDictaLM-3.0-24B-Thinking-FP8-Q4_K_S-GGUFDictaLM-3.0-1.7B-Thinking-Q4_K_M-GGUFDictaLM-3.0-24B-Base-W4A16-Q4_K_S-GGUFDictaLM-3.0-1.7B-Thinking-Q8_0-GGUFvrs-sft-Qwen2_5-7B-itQwen3-1.7B-for-24GB-VRAMVran-27B-SLO-BioMed-Research-GGUF