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.
Qwen3-1.7B_eagle3kimi-k2.6-eagle3-mlasglang-EAGLE3-LLaMA3.1-Instruct-8Bgpt-oss-120b-Eagle3-v3EAGLE3-LLaMA3.1-Instruct-8BEAGLE3-gpt-oss-120b-bf16gpt-oss-120b-Eagle3-short-contextEAGLE3-gpt-oss-20b-bf16sglang-EAGLE-llama2-chat-7BEagle2.5-8Bdeepseek-v3-randomQwen3-8B-speculator.eagle3MiniMax-M3-EAGLE3A.X-K2-EAGLE3tiny-random-qwen3-vl-eagle3qwen3_8b_eagle3SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-NexQwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1SpeculatorLlama3-1-8B-Eagle3-converted-0717-quantizedSpeculator-Qwen3-8B-Eagle3-converted-071-quantizedv5-Eagle-7B-HFLlama-3.1-8B-Instruct-speculator.eagle3EAGLE-LLaMA3.1-Instruct-8BMiniMax-M3-EAGLE3-GQAkimi-k2.6-eagle3.1-mlaEAGLE-LLaMA3-Instruct-8Beagle-deepseek-v3-randomQwen3-8B_eagle3MiniMax-M2.7-EAGLE3-draft-vocab200kSpeculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16