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.
agentica-org_DeepSWE-Preview-GGUFDeepSWE-PreviewQwen3.8-27B-DFlash2-FP16Qwen3.6-35B-A3B-MLX-VL-oQ8-FP16deepswe-k8s-sync-S0b16-c256-replace-tokenexact-step175deepswe-k8s-sync-S0b16-c256-step140to180-step175DeepSWE-Preview-GGUFQwen3.6-35B-A3B-MLX-oQ4-FP16Qwen3.6-35B-A3B-MLX-VL-oQ6Qwen3.6-35B-A3B-MLX-VL-oQ4-FP16Qwen3.6-35B-A3B-MLX-oQ5-FP16agentica-org.DeepSWE-Preview-GGUFQwen3.6-27B-MLX-oQ4-FP16Qwen3.6-35B-A3B-MLX-VL-oQ8Qwen3.6-27B-MLX-oQ5-FP16Qwen3.6-35B-A3B-MLX-oQ8Ornith-1.0-35B-MLX-VL-oQ4-FP16Ornith-1.0-35B-MLX-oQ4-FP16GigaChat3.1-10B-A1.8B-MLX-MXFP4Qwen3.5-9B-MLX-MXFP4Qwen3.6-35B-A3B-MLX-oQ8-FP16Ornith-1.0-35B-MLX-oQ4agentica-org_DeepSWE-Preview-GGUFYandexGPT-5-Lite-8B-Instruct-MLX-MXFP4Qwen3.6-35B-A3B-MLX-oQ4Qwen3.6-27B-MLX-VL-oQ6Qwen3.5-27B-MLX-oQ4Qwen3.6-35B-A3B-MLX-VL-oQ6-FP16Qwen3.6-35B-A3B-MLX-VL-oQ4Qwen3.6-27B-DFlash-FP16
