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.
Qwen3.8-27B-NVFP4-RTX5090Qwen3.8-27B-Uncensored-NVFP4-RTX5090Qwen3.8-27B-NVFP4-RTX5090-LMHead4Qwen3.8-27B-RTX5080Qwen3.8-27B-Uncensored-DSpark-RTX5090Swift-1.5-Qwen3.8-27B-W4A16-RTX3090-NInfer-v3Huihui-Qwen3.8-27B-Abliterated-Gittensor-Style-NVFP4-RTX5090DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000Qwen3.8-27B-NVFP4-RTX5090-LMHead4Qwen3.8-27B-Uncensored-W4A16-RTX3090-MTP4rtx5090_uncensored_optimized-qwen3-coder-30b-a3b-merged-ggufQwen3.8-27B-Uncensored-W4A16-RTX3090-MTP4DeepSeek-v4.1-Flash-EXL3-2.0bpw-Ablit-EngramQ4-SM120-Dual-RTX-Pro-6000RTX3090x2_-_krx-it-v0.3.4-test-ggufQwen3.8-27B-Uncensored-W4A16-RTX3090-MTP4-embed-int4RTX3090x2_-_qwen2.5-7B-Instruct-v0.2.9-v0.3-ggufQwen3.8-Flash-Next-NVFP4-FP8-Pruned-RTXPRO-6000Qwen3.8-27B-Uncensored-NVFP4-RTX5090Ternary-Bonsai-2-27B-RTX4070flux2dev-fp8-transformer-rtx5090-sm120qwen3.8-27b-w4a16-autoround-rtx3090Qwen3.8-27B-Digisensus-NVFP4-RTX5090-256KQwen3.8-27B-NVFP4-RTX5090-No-MTPQwen3.6-35B-A3B-I-Mini-RTX4070qwen2.5-grpo-gsm8k-rtx3060Swift-Qwen3.8-27B-NVFP4-RTX5090natural-lora-rtx3090FineTune_LLama3.1_4Bit_Use_jojo0217_korean_safe_conversation_and_unsloth_with_RTX3090flux2-dev-quantized-rtx-4090LFM2.5-2.6B-Windows-RTX-CUDA-GGUF
