Join the AMD Open Robotics Hackathon
•
12
AI & ML interests
None defined yet.
Recent Activity
Papers
Instella: Fully Open Language Models with Stellar Performance
XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models
Articles
amd/Qwen2.5-7B-Instruct-awq-uint4-asym-g128-lmhead-g32-fp16-onnx-hybrid
Text Generation
•
Updated
•
34
amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-fp16-onnx-hybrid
Text Generation
•
Updated
•
20
amd/Phi-3.5-mini-instruct-awq-g128-int4-asym-fp16-onnx-hybrid
Text Generation
•
Updated
•
11
amd/Llama-3.2-3B-Instruct-awq-g128-int4-asym-fp16-onnx-hybrid
Updated
•
38
amd/Llama-3.2-1B-Instruct-awq-g128-int4-asym-fp16-onnx-hybrid
Updated
•
58
amd/Qwen2.5-1.5B-Instruct-ptpc-Quark-ts
2B
•
Updated
•
2.03k
amd/AMD-Hummingbird-I2V
Updated
•
8
amd/zebra_4MLA12M2_8bt_SFT_8k_combined
2B
•
Updated
•
3
amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-bf16-onnx-ryzen-strix
Text Generation
•
Updated
•
29
•
2
amd/Phi-3-mini-4k-instruct-awq-g128-int4-asym-fp16-onnx-hybrid
Text Generation
•
Updated
•
28
amd/Auto-Mixed-Precision-Mixtral-8x7B-Instruct-v0.1-Weight-Activation-Mixed-MXFP4-FP8PT-KVFP8
Updated
amd/grok-1-W4A8KV8
Updated
•
1.87k
•
2
amd/OGA_DML_Qwen_Qwen2.5-1.5B-Instruct
Text Generation
•
Updated
amd/OGA_DML_Qwen_Qwen2.5-3B-Instruct
Text Generation
•
Updated
amd/Phi4-multimodal-instruct
6B
•
Updated
•
3
amd/Llama-2-70b-chat-hf-WMXFP4-AMXFP4-KVFP8-Scale-UINT8-MLPerf-GPTQ
37B
•
Updated
•
113
amd/Mixtral-8x7B-Instruct-v0.1_FP8_MLPerf_V3
47B
•
Updated
•
13
amd/NPU-Whisper-Base-Small
Updated
•
4
amd/Llama-3.1-8B-awq-g128-int4-onnx-directml
Updated
amd/Llama-3.1-8B-Instruct-awq-g128-int4-onnx-directml
Updated
amd/EVLM-3B
4B
•
Updated
•
5
amd/Mistral-7B-v0.1-FP8-KV
7B
•
Updated
•
3
•
1
amd/Llama-3.2-11B-Vision-Instruct-FP8-KV
11B
•
Updated
•
84
•
1
amd/dbrx-base-FP8-KV
132B
•
Updated
•
17
amd/NPU-ESRGAN-ryzen-strix-cpp
Updated
•
2
amd/Instella-T2I
Updated
•
8
•
10
amd/Nitro-T-0.6B
Text-to-Image
•
Updated
•
9
•
4
amd/Nitro-T-1.2B
Text-to-Image
•
Updated
•
40
•
7
amd/PARD-Qwen3-0.6B
Text Generation
•
0.8B
•
Updated
•
77
•
1
amd/Llama-3.3-70B-Instruct-FP8-KV
71B
•
Updated
•
4.15k
•
4