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_eagle3EAGLE3-LLaMA3.1-Instruct-8Bsglang-EAGLE3-LLaMA3.1-Instruct-8Bgpt-oss-120b-Eagle3-v3kimi-k2.6-eagle3-mlaEAGLE3-gpt-oss-120b-bf16MiniMax-M3-EAGLE3EAGLE3-gpt-oss-20b-bf16Qwen3-8B-speculator.eagle3Llama-3.1-8B-Instruct-speculator.eagle3SGLang-EAGLE3-Qwen3-30B-A3B-Instruct-2507-SpecForge-Nexgpt-oss-120b-Eagle3-short-contexttiny-random-qwen3-vl-eagle3Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1SpeculatorLlama3-1-8B-Eagle3-converted-0717-quantizedkimi-k2.6-eagle3.1-mlaMiniMax-M3-EAGLE3-GQASpeculator-Qwen3-8B-Eagle3-converted-071-quantizedqwen3_8b_eagle3A.X-K2-EAGLE3MiniMax-M2.5-Eagle3Qwen3-8B_eagle3Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16Qwen3-4B_eagle3sglang-EAGLE3-Llama-3.1-Instruct-8Bgemma-4-31B-it-speculator.eagle3gpt-oss-120b-Eagle3-long-contextqwen3_30b_moe_eagle3gpt-oss-120b-speculator.eagle3MiniMax-M2.7-EAGLE3-draft-vocab200k