nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors
Text Generation • 8B • Updated • 36 • 2
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token-2048-Samples
Text Generation • 8B • Updated • 136
nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token
Text Generation • 8B • Updated • 136
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test
Text Generation • 8B • Updated • 133
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 1.95k • 1
nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test
Text Generation • 8B • Updated • 217
nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test
Text Generation • 8B • Updated • 130
nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test
Text Generation • 8B • Updated • 124
nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors
Text Generation • 8B • Updated • 125
nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V
Text Generation • 8B • Updated • 21
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos
Text Generation • 8B • Updated • 29
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 15.2k
nm-testing/Llama-3.2-1B-instruct-attn-quant
1B • Updated • 18
nm-testing/Llama-3.2-1B-Instruct-transformed-w4a16
1B • Updated • 22
nm-testing/Llama-3.2-1B-Instruct-group-activations
1B • Updated • 16
nm-testing/Llama-3.2-1B-Instruct-attention-fp8-head
1B • Updated • 17
nm-testing/Llama-3.1-8B-Instruct-QKV-FP8-tensor-static_minmax
8B • Updated • 14
nm-testing/Llama-3.1-8B-Instruct-QKV-FP8-attn_head-static_minmax
8B • Updated • 19
nm-testing/Llama-3.1-8B-Instruct-QKV-FP8-Tensor
8B • Updated • 16
nm-testing/Llama-3.1-8B-Instruct-QKV-FP8-Head
8B • Updated • 19
nm-testing/Llama-3.1-8B-Instruct-KV-FP8-tensor-static_minmax
8B • Updated • 89
nm-testing/Llama-3.1-8B-Instruct-KV-FP8-attn_head-static_minmax
8B • Updated • 21
nm-testing/Llama-3.1-8B-Instruct-KV-FP8-Tensor
8B • Updated • 18
nm-testing/Llama-3.1-8B-Instruct-KV-Cache-FP8
8B • Updated • 22
nm-testing/DeepSeek-R1-Distill-Qwen-14B2of4-W8A8-FP8-Dynamic-Per-Token
15B • Updated • 29
nm-testing/Qwen3.8-27B-NVFP4-FP8
20B • Updated • 61
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Static-Asym-e2e
1B • Updated • 21
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Asym-e2e
1B • Updated • 21
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A16-e2e
1B • Updated • 20
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A16_channel-e2e
1B • Updated • 18