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.
Qwen3-8B-f16Qwen3-0.6B-f16Qwen3-4B-f16Qwen3-1.7B-f16Qwen3-14B-f16Qwen3-Coder-30B-A3B-Instruct-f16Qwen3-32B-f16ganymede-24b-f16GLM-5.3-Flash-Abliterated-Heretic-V1-UD-IQ4_XS-F16Qwen2.5-Coder-14B-Instruct-F16-GGUFLlama3-8B-Chinese-Chat-GGUF-f16TinyLLama-v0-5M-F16-llamafileMeta-Llama-3.1-8B-Instruct-GGUF-f16Hermes-Kimiko-13B-f16-GGUFNSFW-RP-RolePlay-LoRA-ArliAI-Llama-3.1-8B-F16-GGUFQwen2.5-Coder-1-5B-Instruct-f16-q4_k_mMeta-Llama-3-1-8B-Instruct-f16-ggufOFFFELLIA_f16_IBM_Granite-4.2-3b.ggufgemma-4-e2b-it-istara-ux-research-MLX-F16miiqu-f16Qwen3.5-4B-APIGen-MT-5k-F16-GGUFDeepSeek-R1-Distill-Qwen-1-5B-f16-iq2_xxs-GGUFaction-gemma-2-2b-it-vllm-f16DeepSeek-R1-Distill-Qwen-1-5B-f16-iq3_xxs-GGUFQwen3-4b-Z-Image-Engineer-V4-F16phi-2-insurance_qa-sft-lora-gguf-f16gemma-3-1b-thinking-gguf-F16Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-f16dj-llama3-F16-GGUFEvaGPT-German-Mistral-LlamaTok-DE-7.2B-f16-V9.1.2
