Hugging Face's logo
amd 's Collections
HyLo: Long-Context Aware Upcycling for Hybrid LLMs
Ryzen AI — NPU Medusa 0.9.2 LLM Models
Ryzen AI 1.8.0 — Hybrid
Ryzen AI 1.8.0 — NPU 4K
Ryzen AI 1.8.0 — NPU 16K
Ryzen-AI-1.8.0 — SD Models
Ryzen AI Whisper NPU Optimized ONNX models
AMD Developer Cloud One Click Models
Instella-MoE ✨
zentorch Quantized Models - LLM-Compressor v0.11.0
zentorch Quantized Models - LLM-Compressor v0.10.0.2
PARD-2
zentorch TorchAO Quantized Models - PyTorch 2.11
zentorch TorchAO Quantized Models - PyTorch 2.10
Ryzen AI 1.7.1 — NPU LFM2 Models
Ryzen AI 1.7.1 — NPU 16K
Ryzen AI 1.7.1 — NPU 4K
Ryzen AI 1.7.1 — Hybrid
Ryzen-AI-1.7-NPU-LLM_V2
LuminaSFT
Micro-World
Ryzen-AI-1.7-NPU-creativity-models
Ryzen-AI-1.7-NPU-LLM
Ryzen-AI-1.7-Hybrid-LLM
ReasonLite
SAND
Hummingbird
Ryzen-AI-1.6-NPU-LLM
Ryzen-AI-1.6-Hybrid-LLM
Quark Quantized Auto Mixed Precision (AMP) Models
Quark ByteDance Models
OGA_CPU_8_8_2025
OGA_DML_8_6_2025
Dell Pro AI Studio
Quark Quantized PTPC FP8 Models
RyzenAI-1.5_LLM_Hybrid_Models
RyzenAI-1.5_LLM_NPU_Models
Gumiho
PARD
OGA FP32 CPU models
WCR-4-30
OGA CPU LLM Collection
Quark Quantized MXFP4 Models
Quark Quantized DeepSeek Models
Quark Quantized LLaMA4 Models
RyzenAI-finetuned-local-LLMs
AMDGPU OnnxGenAI
RyzenAI-1.4_LLM_NPU_Models
RyzenAI-1.4_LLM_Hybrid_Models
Instella-VL✨
Instella ✨
AMD-HybridLM-Models ✨
AMD-RyzenAI-Deepseek-R1-Distill-Hybrid
AMDGPU onnx
RyzenAI-1.3_LLM_NPU_Models
RyzenAI-1.3_LLM_Hybrid_Models
Quark Quantized INT8 Models
Nitro Diffusion 💥
Quark Quantized Diffusion Models
AMD-OLMo
Quark Quantized ONNX LLMs for Ryzen AI 1.3 EA
Quark Quantized OCP FP8 Models
Quark ONNX: int8 Quantized Models
Quark Quantized INT4 Models
Quark Quantized INT4 ONNX Models

HyLo: Long-Context Aware Upcycling for Hybrid LLMs

Hybrid MLA + Gated DeltaNet / Mamba-2 models from long-context aware upcycling: up to 32x usable context with over 90% KV-cache reduction.