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.
Qwimi3.5-9B-Kimik2.6-Opus-Distill-MTP-GGUFQwen3-32B-Kimi-K2-Thinking-Distill-GGUFQwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-i1-GGUFQwen3.5-27B-kimi-k2.5-Reasoning-Distilled-i1-GGUFKimi-K2.5-BF16-Pruned-20B-i1-GGUFKimi-K2.7-Code-MLX-3.6bitQwen3-32B-Kimi-K2-Thinking-Distill-i1-GGUFKimi-K2.7-Code-4bitQwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-GGUFQwen3.5-27B-kimi-k2.5-Reasoning-Distilled-GGUFQwen3-4B-Thinking-2507-Kimi-K2-Thinking-Distill-i1-GGUFQwen3-32B-Kimi-K2-Thinking-Distill-GGUFKimi-K2.5-BF16-Pruned-20B-GGUFqwen3.5_4B_AiO_LR_lora_kimi_k2.5_distilationKimi-K2.7-Code-GGUFQwen3-4B-Thinking-2507-Kimi-K2-Thinking-Distill-GGUFDialoGPT-medium-distill-Kimi-K2-Instruct-GGUFKimi-K2.5-MLX-2.8bitKimi-K2-Instruct-0905-control-vectorsKimi-K2.6-MLX-3.6bitKimi-K2.7-Code-MLX-Q3iKimi-K2.5-MLX-2.5bitKimi-K2-Instruct-0905-MLX-2bitKimi-K2.6-MLX-3.3bitKimi-K2-Instruct-quantized.w4a16Kimi-K2-Instruct-0905-MLX-4bitKimi-K2-Instruct-0905-MLX-8bitKimi-K2-Instruct-0905-MLX-6bitkimi-k2.7-code-eagle3-mlaQwen3-4B-Thinking-2507-Kimi-K2-Thinking-Distill-GGUF
