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.
Qwen3-8BQwen3-8B-AWQQwen3-8B-FP8Qwen3-8B-GGUFQwen3-8B-BaseQwen3-8B-GGUFQwen3-8B-4bitQwen3-8B-NVFP4Qwen3-8B-unsloth-bnb-4bitQwen3-8B-GGUFQwen3-8BQwen3-8B-64k-Context-2X-Josiefied-UncensoredQwen3-8B-MLX-4bitQwen3-8B-GGUFQwen3-8B-MLX-8bitqwen38-flash-next-v3Qwen3-8B-bnb-4bitQwen3-8B-Hivemind-Instruct-Heretic-Abliterated-Uncensored-NEO-Imatrix-GGUFQwen3-8B-speculator.eagle3Qwen3-8B-Q8_0-full-v2.ggufqwen38-27b-hca-spliceQwen3-8B-DFlash-b16Qwen3-8B-quantized.w4a16Qwen3-8B-GGUFqwen3-8b-peagle-speculatorsQwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1Qwen3-8B-speculators.peagle-qwen3arch-ckpt4qwen3_8b_eagle3Qwen3-8B-Q4_K_M-GGUFQwen3-8B-abliterated-GGUF
