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.
qwen1-0-7_sft_16bit_vllmgemma-4-26B-A4B-it-W4A16-vLLMkaggle-vllm-modelsqwen3-1-5_sft_16bit_vllmPinkstack_Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUFpalmyra-vision-vllmqwen3_1.7b_summary_v10_vllmMiniCPM4-8B-Eagle-vLLMQwen3.6-35B-A3B-Heretic-REAP-0.30-GPTQ-Pro-vLLMMiniCPM4-8B-marlin-Eagle-vLLMMeta-Llama-3.1-8B-Instruct-vllm-fp8MiniCPM4-8B-marlin-vLLMaction-gemma-2-2b-it-vllm-f16talkie-1930-13b-it-vllmlm-playschool-qwen3.5-2b-sft-dpo-vllmLFM2.5-8B-A1B-Q4_K_M-dequant-bf16-vllmMistral-Nemo-Instruct-2407-vllm-fp8NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllmQwopus3.5-27B-v3-FP8-vllm-readyaischeduler-vllm-bf16vllm-gemma-3-12b-Instruct-indonesian-legal-finetunehoa-1b4Qwen3-8B-ep4_julia_codeforces_extended_with_thinksft_16bit_vllmexp_22_1_grpo_checkpoint_180_16bit_vllmexp_22_0_grpo_checkpoint_340_16bit_vllmNVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllmdsc_julia_sftsft_16bit_vllmtalkie-1930-13b-base-vllmQwen2.5-14B-Instruct-H3-VLLM-testturn-detection-cocalai-vllm