nm-testing/granite-8b-code-instruct-128k-W8A8-Dynamic-Per-Token
8B • Updated • 4
nm-testing/granite-3.1-8b-instruct-W4A16-G128
8B • Updated • 6
nm-testing/granite-3.1-8b-instruct-W8A8-Dynamic-Per-Token
8B • Updated • 5
nm-testing/DeepSeek-R1-Distill-Qwen-14B2of4-sparse
15B • Updated • 6
nm-testing/Mistral-7B-Instruct-v0.3-FP8-Dynamic
7B • Updated • 14
nm-testing/DeepSeek-R1-Distill-Qwen-14B-W4A16-G128
15B • Updated • 4
nm-testing/granite-8b-code-instruct-128k-FP8-Dynamic
8B • Updated • 4
nm-testing/DeepSeek-R1-Distill-Qwen-14B-W8A8-Dynamic-Per-Token
15B • Updated • 13
nm-testing/granite-3.1-8b-instruct-FP8-Dynamic
8B • Updated • 4
nm-testing/DeepSeek-R1-Distill-Qwen-14B-FP8-Dynamic
15B • Updated • 3
nm-testing/llama2.c-stories42M-pruned2.4-compressed
48.6M • Updated • 39
nm-testing/granite-3.1-2b-instruct-W4A16-G128
3B • Updated • 3
nm-testing/DeepSeek-R1-Distill-Qwen-1.5B-W4A16-G128
2B • Updated • 136
nm-testing/whisper-large-v2-W4A16-G128
2B • Updated • 3
nm-testing/whisper-tiny-W4A16-G128
58M • Updated • 4
nm-testing/llama2.c-stories42M-quantized-fp8-Dynamic
58.1M • Updated • 5
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Per-Token-compressed
1B • Updated • 868
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A16-G128-compressed
1B • Updated • 1.01k
nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-compressed
1B • Updated • 960
nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-Dynamic-compressed
1B • Updated • 1.6k
nm-testing/granite-3.1-3b-a800m-instruct-w4a16
3B • Updated • 12
nm-testing/llama-2-7b-sparse2of4
7B • Updated • 7
nm-testing/test-w4a16-mixtral-actorder-group
47B • Updated • 568
nm-testing/llama2.c-stories15M-gsm8k-pruned.2of4-BitMask
22.2M • Updated • 6
nm-testing/llama2.c-stories15M-gsm8k-pruned.2of4-Uncompressed
24.4M • Updated • 9
nm-testing/gemma-2-9b-it-FP8-dynamic-KV
10B • Updated • 6
nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-tensor_wts_tensor_act_int8-BitM
5B • Updated • 5
nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-tensor_wts_tensor_act_fp8-BitM
5B • Updated • 6
nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-tensor_wts_per_tok_dyn_act_int8-BitM
5B • Updated • 4
nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-tensor_wts_per_tok_dyn_act_fp8-BitM
5B • Updated • 5