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.
flash-attn3reluflash-attn2triton-layer-normvllm-flash-attn3activationfinegrained-fp8causal-conv1dgpt-oss-triton-kernelsmamba-ssmcv-utilsmegablocksquantization-bitsandbytesflash-attn4SmolLM3-3B-trellis-3inst-4bpw-kernelrotaryliger-kernelsDeepSeek-V4.1-Flash-MXFP4-GGUFfacebook_KernelLLM-GGUFKernelLLM-GGUFMini-K3-1H-kda-kernel-32-v2_DMini-K3-1H-kda-kernel-64-v2Mini-K3-1H-kda-kernel-16-v2Mini-K3-1H-kda-kernel-0-v2Mini-K3-1H-kda-kernel-2-v2Mini-K3-1H-kda-kernel-1-v2Mini-K3-1H-kda-kernel-8-v2_Ddeformable-detrpaged-attentiondeep-gemm