Collection on FP8 Quantization of Weights, Activations and KV Cache
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
-
nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors
Text Generation • 8B • Updated • 10 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated • 6 -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 16.8k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 5.91k • 1
Collection on FP8 Quantization of Weights, Activations and KV Cache
-
nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors
Text Generation • 8B • Updated • 10 • 2 -
nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform
Text Generation • 8B • Updated • 6 -
nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test
Text Generation • 8B • Updated • 16.8k -
nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test
8B • Updated • 5.91k • 1
models 523
nm-testing/w8a16_grouped_quant-e2e
1B • Updated • 574
nm-testing/w4a16_sym_awq-e2e
1B • Updated • 481 • 2
nm-testing/w4a16_grouped_quant-e2e
1B • Updated • 513
nm-testing/w4a16_asym_awq-e2e
1B • Updated • 559
nm-testing/w4a16_actorder_weight-e2e
1B • Updated • 531
nm-testing/w4a16_actorder_group-e2e
1B • Updated • 540
nm-testing/nvfp4_fp8_mixed-e2e
0.8B • Updated • 526
nm-testing/multiple_modifiers_gptq_awq_disk-e2e
0.9B • Updated • 352
nm-testing/multiple_modifiers_gptq_awq-e2e
0.9B • Updated • 568 • 1
nm-testing/model_free_nvfp4a16-e2e
0.7B • Updated • 104
datasets 6
nm-testing/ultrachat_gpt_oss_20b_hidden_states
Updated • 287 • 1
nm-testing/sharegpt_qwen3_8b_hidden_states
Updated • 323
nm-testing/ultrachat_qwen3_8b_hidden_states
Updated • 311
nm-testing/sharegpt_llama3_8b_token_freq
Updated • 28
nm-testing/sharegpt_llama3_8b_hidden_states
Viewer • Updated • 1 • 254
nm-testing/qa-chat-prompts
Viewer • Updated • 200 • 51 • 2