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.
GLM-5.3-Quark-MXFP4-AttnFP8falcon-no-parallel-attn-testattnres4babylm2026-10m-l32-static-s1339attnres4babylm2026-10m-l32-static-s1337attnres4babylm2026-10m-l32-static-s1338attnres4babylm2026-100m-l32-dynamic-s1339attnres4babylm2026-100m-l32-baseline-s1339attnres4babylm2026-10m-l32-dynamic-s1338attnres4babylm2026-10m-l32-baseline-s1339attnres4babylm2026-10m-l32-dynamic-s1339attnres4babylm2026-10m-l32-baseline-s1338attnres4babylm2026-100m-l32-baseline-s1337attnres4babylm2026-100m-l32-dynamic-s1337attnres4babylm2026-100m-l32-baseline-s1338attnres4babylm2026-100m-l32-dynamic-s1338attnres4babylm2026-10m-l32-baseline-s1337attnres4babylm2026-10m-l16-baseline-s1338attnres4babylm2026-10m-l16-baseline-s1337SeerAttention-Llama-3.1-8B-AttnGatesattnres4babylm2026-10m-l16-dynamic-s1338attnres4babylm2026-10m-l16-baseline-s1339attnres4babylm2026-10m-l32-dynamic-s1337attnres4babylm2026-10m-l16-dynamic-s1339attnres4babylm2026-10m-l16-dynamic-s1337SeerAttention-Qwen2.5-7B-AttnGatesSeerAttention-Decode-Qwen3-4B-AttnGatesSeerAttention-Decode-Qwen3-8B-AttnGatesMixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-HQQoasst-pythia-12b-flash-attn-5000-stepsMiniMax-M2.5-Hybrid-AWQ-W4A16G128-Attn-fp8_e4m3-KV-fp8_e4m3