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.
DeepSeek-R1-Distill-Qwen-1.5B-SpeculativeReasonerDeepSeek-R1-Distill-Qwen-1.5B-GRPO-SpeculativeReasoner-GGUFQwen3-8B-speculative-sft-1epQwen2.5-Coder-1.5B-32B-speculative-GGUFqwen3-0.6B-speculative-gguf-sspeculative-cascadesDeepSeek-R1-Distill-Qwen-1.5B-GRPO-SpeculativeReasonerDeepSeek-R1-Distill-Qwen-1.5B-GRPO-SpeculativeReasoner_Minillama2-13b-chat-poss3qwen2.5-1.5B-speculative-paddedQwen-2.5-1.5b-mtp-speculativeqwen2.5-0.5B-speculative-paddedllama2-13b-chat-poss1qwen2.5-3B-speculative-paddedQwen3-Omni-30B-A3B-NPU2-SPECULATIVE-UNSUPPORTEDllama2-13b-chat-poss2llama3-8b-instruct-poss2Speed-E3-Llama3.1-8B-Instruct-vllmllama3-8b-instruct-poss3llama3-8b-instruct-poss1slurp-speculative_ft-model_distill_whisper_largev2llama3-8b-instruct-eagle-reproducelm-head-for-speculative-pruningspeculative-pruning-mlpSpeed-E3-Llama3.1-8B-Instructspeculativellama3-8b-instruct-hass-reproduceSpeculative_datasetsCoE_Speculative_Draft_Datasetsspeculative-decoding-cross-domain-analysis