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.
vllm-translategemma-12b-itQwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED-FP8-vLLMOrnith-1.5-35B-A3B-PrismaQuant-AQUA-25GB-vllmGritLM-7B-vllmTernary-Bonsai-2-27B-vllmqwen1-0-7_sft_16bit_vllmQwen3.8-27B-DFlash2-fp8-vllmLumina-mGPT-7B-768kaggle-vllm-modelsNameless-86-pql-model-vllm-GGUFdat-lequoc-vLLM-fast-apply-16bit-v0.13-Llama3.2-1B-GGUFdat-lequoc-vLLM-fast-apply-16bit-v0.12-Llama3.2-1B-GGUFqwen3-1-5_sft_16bit_vllmgemma-4-26B-A4B-it-W4A16-vLLMQwen3.8-27B-PrismaAQUA-gridbook-13GB-5080-vllmQwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-PrismaQuant-8bit-vllmpalmyra-vision-vllmSuperGemma4-26B-Abliterated-Multimodal-NVFP4-vLLMOpenEuroLLM-Czech-vLLM-GGUFLightOnOCR-2-1B-vi-vllmPinkstack_Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUFGemma4-31B-IT-PrismaQuant-5.5bit-vllmsnowflake-arctic-instruct-vllmLFM2.5-8B-A1B-Q4_K_M-dequant-bf16-vllmqwen3_1.7b_summary_v10_vllmLaguna-S-2.1-ModelOpt-NVFP4-W4A4-KVcal-vllmQwen3.6-35B-A3B-Heretic-REAP-0.30-GPTQ-Pro-vLLMMiniCPM4-8B-Eagle-vLLMMiniCPM4-8B-marlin-Eagle-vLLMMiniCPM4-8B-marlin-vLLM