AMD

Team

company

Verified

http://www.amd.com/

AMD

amd

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

bconsolvo updated a model about 10 hours ago

amd/ryzenai-sesr

gguasti updated a model 1 day ago

amd/stable-diffusion-1.5-amdnpu

bowenbaoamd updated a model 1 day ago

amd/Kimi-K2-Thinking-W4A8

View all activity

Papers

Instella: Fully Open Language Models with Stellar Performance

XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models

View all Papers

Articles

Join the AMD Open Robotics Hackathon

Nov 13, 2025

•

amd 's collections 35

Ryzen-AI-1.7-NPU-creativity-models

amd/ryzenai-realesrgan

Updated 14 days ago
amd/ryzenai-psfrgan

Updated 14 days ago
amd/ryzenai-sesr

Updated about 10 hours ago
amd/ryzenai-hrnet-bg-seg

Image Segmentation • Updated 14 days ago

Ryzen-AI-1.7-Hybrid-LLM

amd/Qwen3-14B-onnx-ryzenai-1.7-hybrid

Text Generation • Updated 8 days ago • 2
amd/Qwen2.5-14B-instruct-onnx-ryzenai-1.7-hybrid

Text Generation • Updated 8 days ago
amd/SmolLM2-135M-Instruct-onnx-ryzenai-1.7-hybrid

Text Generation • Updated 9 days ago
amd/SmolLM-135M-Instruct-onnx-ryzenai-1.7-hybrid

Updated 9 days ago

SAND

amd/SAND-Math-Qwen2.5-32B

Text Generation • 33B • Updated Dec 6, 2025 • 25 • 3
amd/SAND-MathScience-DeepSeek-Qwen32B

Text Generation • 33B • Updated Dec 6, 2025 • 9 • 2
amd/SAND-Post-Training-Dataset

Viewer • Updated Dec 6, 2025 • 27.9k • 177 • 3
amd/SAND-MATH

Viewer • Updated Oct 17, 2025 • 16.9k • 548 • 3

Ryzen AI 1.7 Whisper NPU Optimized ONNX models

amd/whisper-small-onnx-npu

Updated 19 days ago
amd/whisper-medium-onnx-npu

Updated 5 days ago
amd/whisper-large-turbo-onnx-npu

Updated 19 days ago • 2
amd/whisper-base-onnx-npu

Updated 5 days ago

Ryzen-AI-1.6-Hybrid-LLM

amd/AMD-OLMo-1B-SFT-DPO-onnx-ryzenai-hybrid

Updated Oct 23, 2025
amd/CodeLlama-7b-Instruct-hf-onnx-ryzenai-hybrid

Updated Oct 23, 2025 • 5 • 2
amd/DeepSeek-R1-Distill-Llama-8B-onnx-ryzenai-hybrid

Updated Oct 23, 2025 • 141 • 1
amd/DeepSeek-R1-Distill-Qwen-1.5B-onnx-ryzenai-hybrid

Updated Oct 23, 2025 • 3

Quark ByteDance Models

amd/DeepSeek-R1-0528-MXFP4-ASQ

342B • Updated Dec 12, 2025 • 42 • 1
amd/Llama-3.3-70B-Instruct-MXFP4-Preview

38B • Updated Nov 6, 2025 • 2.47k • 2
amd/Llama-3.1-405B-Instruct-MXFP4-Preview

218B • Updated Nov 6, 2025 • 445 • 1

Dell Pro AI Studio

Model for Dell Pro AI studio

amd/NPU-Whisper-Base-Small

Updated Jul 30, 2025 • 4
amd/NPU-Nomic-embed-text-v1.5-ryzen-strix-cpp

Updated Nov 17, 2025 • 3
amd/NPU-ESRGAN-ryzen-strix-cpp

Updated Jul 17, 2025 • 2
amd/NPU-CLIP-Python

Updated Oct 6, 2025 • 1

RyzenAI-1.5_LLM_Hybrid_Models

amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation • Updated Aug 27, 2025 • 18
amd/Phi-3.5-mini-instruct-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation • Updated Sep 16, 2025 • 3
amd/Mistral-7B-Instruct-v0.3-awq-g128-int4-asym-fp16-onnx-hybrid

Updated Sep 16, 2025 • 8
amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation • Updated Sep 16, 2025 • 4

Gumiho

Official Model Parameters for "Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding"

Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding

Paper • 2503.10135 • Published Mar 13, 2025
amd/Gumiho-llama2-70b

Updated Jun 12, 2025
amd/Gumiho-llama2-7b

Updated Jun 12, 2025
amd/Gumiho-llama3-70b

Updated Jun 12, 2025

OGA CPU LLM Collection

This collection contains AMD-Quark quantized OGA exported models for CPU execution

amd/Phi-3-mini-4k-instruct_int4_float16_onnx_cpu

Updated Apr 12, 2025
amd/Qwen1.5-7B-Chat_uint4_asym_g128_float16_onnx_cpu

Updated Apr 12, 2025
amd/DeepSeek-R1-Distill-Llama-8B-awq-asym-uint4-g128-lmhead-onnx-cpu

Text Generation • Updated Jan 30, 2025
amd/Llama-3.2-1B-Instruct-awq-uint4-float16-cpu-onnx

Updated Apr 28, 2025

Quark Quantized DeepSeek Models

amd/DeepSeek-R1-MXFP4

371B • Updated Nov 6, 2025 • 18.2k • 5
amd/DeepSeek-R1-MXFP4-ASQ

363B • Updated Nov 6, 2025 • 30 • 1
amd/DeepSeek-R1-0528-MXFP4

363B • Updated Nov 27, 2025 • 8.73k • 1
amd/DeepSeek-R1-0528-MXFP4-ASQ

342B • Updated Dec 12, 2025 • 42 • 1

RyzenAI-1.4_LLM_NPU_Models

amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Aug 27, 2025 • 12 • 2
amd/Phi-3.5-mini-instruct-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Sep 16, 2025 • 34 • 3
amd/Mistral-7B-Instruct-v0.3-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Updated Sep 16, 2025 • 16
amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Jun 28, 2025 • 2 • 1

Instella-VL✨

amd/Instella-VL-1B

1B • Updated Mar 7, 2025 • 128 • 6

AMD-HybridLM-Models ✨

AMD-HybridLM is a family of post-trained, highly efficient hybrid models, designed to combine performance with speed and memory efficiency.

amd/Zebra-Llama-1B-4MLA-12Mamba-DPO

Updated Sep 23, 2025 • 52
amd/Zebra-Llama-1B-4MLA-12Mamba-SFT

Updated Sep 23, 2025 • 11
amd/Zebra-Llama-1B-8MLA-8Mamba-DPO

Updated Sep 23, 2025 • 83
amd/Zebra-Llama-1B-8MLA-8Mamba-SFT

Updated Sep 23, 2025 • 1

AMDGPU onnx

optimized image generation ONNX models for AMD Ryzen (TM) AI GPUs and Radeon Discrete GPUs

amd/stable-diffusion-xl-1.0_io32_amdgpu

Text-to-Image • Updated Dec 17, 2025 • 28
amd/stable-diffusion-1.5_io32_amdgpu

Text-to-Image • Updated Dec 17, 2025 • 19
amd/stable-diffusion-xl-1.0_io16_amdgpu

Updated Apr 3, 2025 • 3
amd/stable-diffusion-1.5_io16_amdgpu

Text-to-Image • Updated Apr 3, 2025 • 17

RyzenAI-1.3_LLM_Hybrid_Models

Models quantized by Quark and prepared for the OGA-based hybrid execution flow (Ryzen AI 1.3)

amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation • Updated Aug 27, 2025 • 18
amd/Phi-3.5-mini-instruct-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation • Updated Sep 16, 2025 • 3
amd/Mistral-7B-Instruct-v0.3-awq-g128-int4-asym-fp16-onnx-hybrid

Updated Sep 16, 2025 • 8
amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation • Updated Sep 16, 2025 • 4

AMD-OLMo

AMD-OLMo are a series of 1 billion parameter language models trained by AMD on AMD Instinct™ MI250 GPUs based on OLMo.

amd/AMD-OLMo

Text Generation • Updated Nov 17, 2025 • 83
amd/AMD-OLMo-1B

Text Generation • 1B • Updated Nov 17, 2025 • 89 • 25
amd/AMD-OLMo-1B-SFT

Text Generation • 1B • Updated Nov 17, 2025 • 64 • 21
amd/AMD-OLMo-1B-SFT-DPO

Text Generation • 1B • Updated Nov 17, 2025 • 38 • 23

Quark Quantized OCP FP8 Models

amd/Llama-3.1-8B-Instruct-FP8-KV

8B • Updated Dec 19, 2024 • 23.4k • 6
amd/Llama-3.1-70B-Instruct-FP8-KV

71B • Updated Dec 19, 2024 • 572 • 4
amd/Llama-3.1-405B-Instruct-FP8-KV

406B • Updated Dec 19, 2024 • 1.99k • 5
amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV

3B • Updated Dec 19, 2024 • 3.36k • 3

Ryzen-AI-1.7-NPU-LLM

List will be updated

amd/Gemma-3-4b-it-mm-onnx-ryzenai-npu

Updated 14 days ago
amd/gpt-oss-20b-onnx-ryzenai-npu

Updated Dec 13, 2025
amd/Phi-4-mini-instruct-onnx-ryzenai-npu

Text Generation • Updated 14 days ago
amd/Qwen2-1.5B-onnx-ryzenai-npu

Text Generation • Updated Oct 23, 2025 • 26 • 1

ReasonLite

amd/ReasonLite-0.6B

0.8B • Updated 13 days ago • 98.9k • 10
amd/ReasonLite-0.6B-Turbo

0.8B • Updated 13 days ago • 29.9k • 7
amd/ReasonLite-Dataset

Viewer • Updated 13 days ago • 6.16M • 408 • 9

Hummingbird

Hummingbird is a series of video generation models built on AMD Instinct™ GPUs, including text-to-video, image-to-videos models.

amd/AMD-Hummingbird-T2V

Text-to-Video • Updated Mar 4, 2025 • 8
amd/AMD-Hummingbird-I2V

Updated Sep 8, 2025 • 8
amd/HummingbirdXT

Updated 22 days ago • 7 • 8

Ryzen-AI-1.6-NPU-LLM

amd/Qwen2-1.5B-onnx-ryzenai-npu

Text Generation • Updated Oct 23, 2025 • 26 • 1
amd/Mistral-7B-Instruct-v0.2-onnx-ryzenai-npu

Updated Oct 23, 2025 • 10
amd/Llama-2-7b-hf-onnx-ryzenai-npu

Text Generation • Updated Oct 8, 2025 • 3
amd/Qwen2-7B-onnx-ryzenai-npu

Text Generation • Updated Oct 23, 2025 • 3

Quark Quantized Auto Mixed Precision (AMP) Models

amd/Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

55B • Updated Sep 26, 2025 • 29
amd/Mixtral-8x7B-Instruct-v0.1-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

37B • Updated Nov 3, 2025 • 27
amd/Qwen3-8B-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

6B • Updated Sep 26, 2025 • 18 • 2
amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8

11B • Updated 14 days ago • 13

OGA_DML_8_6_2025

Models are quantized using quark-0.9, transformers-4.50.0, OGA-0.7.1, ORT-1.21.1 followed by OGA-DML export.

amd/OGA_DML_Qwen_Qwen2.5-3B-Instruct

Text Generation • Updated Aug 8, 2025
amd/OGA_DML_Qwen_Qwen2.5-1.5B-Instruct

Text Generation • Updated Aug 8, 2025

Quark Quantized PTPC FP8 Models

PTPC model quantized by quark

amd/Qwen3-30B-A3B-Thinking-2507-ptpc

31B • Updated Dec 24, 2025 • 13 • 1
amd/Qwen3-VL-235B-A22B-Instruct-ptpc

236B • Updated Dec 24, 2025 • 3
amd/DeepSeek-R1-0528-ptpc

671B • Updated Dec 24, 2025 • 5
amd/DeepSeek-R1-0528-mtp-ptpc

684B • Updated Nov 28, 2025 • 41

RyzenAI-1.5_LLM_NPU_Models

amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Aug 27, 2025 • 12 • 2
amd/Phi-3.5-mini-instruct-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Sep 16, 2025 • 34 • 3
amd/Mistral-7B-Instruct-v0.3-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Updated Sep 16, 2025 • 16
amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Jun 28, 2025 • 2 • 1

PARD

Official Model Parameters for "PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation"

amd/PARD-Llama-3.2-1B

Text Generation • 1B • Updated May 19, 2025 • 379 • 2
amd/PARD-DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • 2B • Updated May 19, 2025 • 29 • 2
amd/PARD-Qwen2.5-0.5B

Text Generation • 0.6B • Updated May 19, 2025 • 183
amd/PARD-Qwen3-0.6B

Text Generation • 0.8B • Updated Jul 9, 2025 • 64 • 2

Quark Quantized MXFP4 models

amd/DeepSeek-R1-MXFP4

371B • Updated Nov 6, 2025 • 18.2k • 5
amd/DeepSeek-R1-MXFP4-ASQ

363B • Updated Nov 6, 2025 • 30 • 1
amd/DeepSeek-R1-0528-MXFP4

363B • Updated Nov 27, 2025 • 8.73k • 1
amd/DeepSeek-R1-0528-MXFP4-ASQ

342B • Updated Dec 12, 2025 • 42 • 1

AMDGPU OnnxGenAI

Collection ONNX GenAI compatible Language Models to run on AMD Ryzen(TM) GPUs and Radeon Discrete GPUs

amd/Llama-2-7b-chat-hf-awq-g128-int4-onnx-directml

Updated Apr 8, 2025
amd/Llama-2-7b-hf-awq-g128-int4-onnx-directml

Updated Apr 10, 2025
amd/Llama-3.1-8B-awq-g128-int4-onnx-directml

Updated Jul 29, 2025
amd/Llama-3.1-8B-Instruct-awq-g128-int4-onnx-directml

Updated Jul 29, 2025

RyzenAI-1.4_LLM_Hybrid_Models

amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation • Updated Aug 27, 2025 • 18
amd/Phi-3.5-mini-instruct-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation • Updated Sep 16, 2025 • 3
amd/Mistral-7B-Instruct-v0.3-awq-g128-int4-asym-fp16-onnx-hybrid

Updated Sep 16, 2025 • 8
amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-fp16-onnx-hybrid

Text Generation • Updated Sep 16, 2025 • 4

Instella ✨

Announcing Instella, a series of 3 billion parameter language models developed by AMD, trained from scratch on 128 Instinct MI300X GPUs.

amd/Instella-3B-Stage1

Text Generation • 3B • Updated Nov 14, 2025 • 29 • 13
amd/Instella-3B

Text Generation • 3B • Updated Nov 14, 2025 • 119 • 40
amd/Instella-3B-SFT

Text Generation • 3B • Updated Nov 14, 2025 • 6 • 11
amd/Instella-3B-Instruct

Text Generation • 3B • Updated Nov 14, 2025 • 112 • 60

AMD-RyzenAI-Deepseek-R1-Distill-Hybrid

amd/DeepSeek-R1-Distill-Llama-8B-awq-asym-uint4-g128-lmhead-onnx-hybrid

Updated Sep 16, 2025 • 21 • 1
amd/DeepSeek-R1-Distill-Qwen-1.5B-awq-asym-uint4-g128-lmhead-onnx-hybrid

Updated Jun 23, 2025 • 3 • 1
amd/DeepSeek-R1-Distill-Qwen-7B-awq-asym-uint4-g128-lmhead-onnx-hybrid

Updated Sep 16, 2025 • 16 • 4

RyzenAI-1.3_LLM_NPU_Models

Models quantized by Quark and prepared for the OGA-based NPU-only execution flow (Ryzen AI 1.3)

amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Aug 27, 2025 • 12 • 2
amd/Phi-3.5-mini-instruct-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Sep 16, 2025 • 34 • 3
amd/Mistral-7B-Instruct-v0.3-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Updated Sep 16, 2025 • 16
amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Jun 28, 2025 • 2 • 1

Nitro Diffusion 💥

Nitro Diffusion is a series of efficient text-to-image diffusion models built on AMD Instinct™ GPUs.

amd/Nitro-1-SD

Text-to-Image • Updated Jun 25, 2025 • 28 • 9
amd/Nitro-1-PixArt

Text-to-Image • Updated Jun 25, 2025 • 27k • 5
amd/Nitro-T-0.6B

Text-to-Image • Updated Jul 9, 2025 • 57 • 5
amd/Nitro-T-1.2B

Text-to-Image • Updated Jul 9, 2025 • 7

Quark Quantized ONNX LLMs for Ryzen AI 1.3 EA

ONNX Runtime generate() API based models quantized by Quark and optimized for Ryzen AI Strix Point NPU

amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Jun 28, 2025 • 2 • 1
amd/Mistral-7B-Instruct-v0.3-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Updated Sep 16, 2025 • 16
amd/Llama-2-7b-hf-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Jun 28, 2025 • 49
amd/Llama-3-8B-awq-g128-int4-asym-bf16-onnx-ryzen-strix

Text Generation • Updated Jun 28, 2025 • 2 • 2