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.
Llama-3.1-8B-Instruct-speculator.eagle3A.X-K2-EAGLE3MiniMax-M2.5-Eagle3Qwen2.5-7B-Instruct-Eagle3qwen2.5-vl-7b-eagle3-sglllama-3.2-3b-instruct-eagle3-sharegpt-sw512-epoch9-step231810Qwen3-VL-8B-Instruct-Eagle3EAGLE3-JPharmatron-7Bqwen3-1.7b-eagle3-sharegpt-sw768-epoch9-step467800Qwen3-VL-2B-Instruct-Eagle3qwen3-1.7b-eagle3-sharegpt-sw512-epoch9-step463620Eagle-1-Mini-i1-GGUFLlama-3.3-70B-Instruct-speculator.eagle3heretic_SmolLM2-1.7B-Eagle-i1-GGUFqwen-2-5-3b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v4qwen3-1.7b-eagle3-sharegpt-sw256-epoch9-step233900qwen3-1.7b-eagle3-sharegpt-sw128-epoch9-step233900kimi-k2.7-code-eagle3-mlaqwen-2_5-1_5b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v4Qwen3-8B-Eagle3Eagle-1-Mini-GGUFqwen-2-5-3b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v3heretic_SmolLM2-1.7B-Eagle-GGUFqwen-2_5-1_5b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-vQwen3-4B-Instruct-2507-Eagle3qwen-2-5-3b-instruct-using-openai-gsm8k-gguf-data-enhanced-with-deepseek-v3-smallMistral-Medium-3.5-128B-EAGLEqwen-2_5-1_5b-instruct-using-codealpaca-20k-enhanced-v1Mistral-Small-4-119B-2603-eagleqwen-2_5-1_5b-instruct-using-openai-gsm8k-data-enhanced-with-deepseek-v2