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_06B_lora_mathHermes-3-Llama-3.1-8B-lorablated-GGUFgemma-4-31b-it-sft-lora-resumed-lastgemma-4-31b-it-lora-lastLlama-3.1-70B-Instruct-lorablated-GGUFHermes-3-Llama-3.1-70B-lorablated-GGUFOpenHermes-2.5-Strix-Philosophy-Mistral-7B-LoRAllama31-8b-knapsack-lora-statelessgranite-3.1-8b-lora-intrinsics-v0.1-GGUFgranite-3.0-8b-lora-intrinsics-v0.1-GGUFqwen3-4b-xlam-function-calling-60k-lorallama32-1b-lora-sft-lab10-modelllama32-1b-lora-sft-lab10-modelLlama-3.1-8B-RAQUEL-TOFU-M-orig-LoRA-v1VLM2Vec-LoRAllama-2-7B-LoRA-assembleoadson-cli-subagent-lora-v2Qwen3-0.6B-Fable5-Reasoning-LoRAGemma-2B-Hinglish-LORA-v1.0-GGUFmistral-7b-arc-sci-lora_09161401Llama-3.1-8B-RAQUEL-TOFU-M-ret-LoRA-v1qwen3-vl-4b-vietnamese-ocr-loraMiniCPM5-2B-Code-loragpt2-DPO-LoRAJun-LoRA-12B-GGUFQwen3-8B-Base-RAQUEL-TOFU-M-orig-LoRA-v1DeepSeek-R1-1.5B-LoRA-Smolexaone-nsmc-lora-merged-wnsduf0000Qwen3-8B-Base-RAQUEL-TOFU-M-ret-LoRA-v1NSFW-RP-RolePlay-LoRA-Qwen-3.5-9B