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-4b-itvllm-translategemma-12b-itQwen3.6-27B-PrismaSCOUT-Blackwell-NVFP4-BF16-vllmjina-embeddings-v4-vllm-retrievalvllm-flash-attn3mmbert-embed-32k-2d-matryoshkavllm-translategemma-12b-itFun-ASR-Nano-2512-vllmVela-1.0-Encoder-307M-Embeddingmmbert32k-intent-classifier-mergedQwen3.8-27B-DSpark-vLLMmmbert32k-jailbreak-detector-mergedvllm-flash-attn3Vela-1.0-Encoder-307M-DomainQwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED-FP8-vLLMmulti-modal-embed-smallmmbert32k-factcheck-classifier-mergedmmbert32k-feedback-detector-mergedQwen3.6-35B-A3B-PrismaQuant-4.75bit-vllmVela-1.0-Encoder-307M-GuardTernary-Bonsai-2-27B-vllmVela-1.0-Encoder-307M-PIImmbert32k-modality-router-mergedvllm-medusa-llama-68m-randomVela-1.0-Encoder-307M-FactCheckQwen3-Reranker-4B-seq-cls-vllm-W4A16Qwen3.8-27B-PrismaAQUA-5.5bit-vllmVela-1.0-Encoder-307M-Feedbackvllm-translategemma-27b-itmmbert32k-pii-detector-merged