nm-testing/Meta-Llama-3-8B-FP8-AttnQuant
8B
•
Updated
•
1
nm-testing/pixtral-12b-FP8-dynamic-all
13B
•
Updated
•
1
nm-testing/pixtral-12b-W4A16-G128
3B
•
Updated
•
1
nm-testing/Pixtral-Large-Instruct-2411-hf
Image-Text-to-Text
•
124B
•
Updated
•
1
nm-testing/Qwen2-VL-2B-Instruct-Sparse-0.6
2B
•
Updated
•
2
nm-testing/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic
Text Generation
•
71B
•
Updated
•
1
•
3
nm-testing/Llama-3.2-11B-Vision-Instruct-quantized.w4a16
Updated
nm-testing/glm-4v-9b-W4A16-G128
14B
•
Updated
•
5
nm-testing/TinyLlama-1.1B-Chat-v1.0-gsm8k-partial-24-remaining-fp8-compressed
1B
•
Updated
•
1
nm-testing/TinyLlama-1.1B-Chat-v1.0-gsm8k-partial-24-entire-fp8-compressed
1B
•
Updated
•
7
nm-testing/TinyLlama-1.1B-Chat-v1.0-gsm8k-partial-24
1B
•
Updated
•
1
nm-testing/TinyLlama-1.1B-Chat-v1.0-gsm8k-full-sparse24
1B
•
Updated
•
1
nm-testing/TinyLlama-1.1B-Chat-v1.0-gsm8k-sparse24-0-5-remaining-fp8-compressed
1B
•
Updated
•
1
nm-testing/whisper-large-v2-FP8-dynamic
2B
•
Updated
nm-testing/TinyLlama-1.1B-Chat-v1.0-gsm8k-sparse24-layer-0-5-fp8-compressed
1B
•
Updated
•
1
nm-testing/TinyLlama-1.1B-Chat-v1.0-gsm8k-sparse24-layer-0-fp8-compressed
1B
•
Updated
•
3
nm-testing/Mistral-7B-Instruct-v0.32of4-W8A8-FP8-Dynamic-Per-Token
7B
•
Updated
•
2
nm-testing/Mistral-7B-Instruct-v0.32of4-sparse
7B
•
Updated
•
1
nm-testing/granite-8b-code-instruct-128k2of4-W8A8-FP8-Dynamic-Per-Token
8B
•
Updated
•
1
nm-testing/granite-8b-code-instruct-128k2of4-sparse
8B
•
Updated
•
1
nm-testing/granite-3.1-8b-instruct2of4-W8A8-FP8-Dynamic-Per-Token
8B
•
Updated
•
2
nm-testing/granite-3.1-8b-instruct2of4-sparse
8B
•
Updated
•
3
nm-testing/Mistral-7B-Instruct-v0.3-W4A16-G128
1B
•
Updated
•
2
nm-testing/Mistral-7B-Instruct-v0.3-W8A8-Dynamic-Per-Token
7B
•
Updated
•
1
nm-testing/granite-8b-code-instruct-128k-W4A16-G128
1B
•
Updated
•
1
nm-testing/granite-8b-code-instruct-128k-W8A8-Dynamic-Per-Token
8B
•
Updated
•
2
nm-testing/granite-3.1-8b-instruct-W4A16-G128
1B
•
Updated
•
1
nm-testing/granite-3.1-8b-instruct-W8A8-Dynamic-Per-Token
8B
•
Updated
•
2
nm-testing/DeepSeek-R1-Distill-Qwen-14B2of4-W8A8-FP8-Dynamic-Per-Token
15B
•
Updated
•
2
nm-testing/DeepSeek-R1-Distill-Qwen-14B2of4-sparse
15B
•
Updated
•
1