nm-testing/w4a16_moe-e2e
31B • Updated • 884
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
nm-testing/Qwen3-30B-A3B-NVFP4-AWQ-e2e
31B • Updated • 371
nm-testing/w8a8_static_asym-e2e
1B • Updated • 378
nm-testing/w8a8_dynamic_asym-e2e
1B • Updated • 386
nm-testing/w8a16_grouped_quant-e2e
1B • Updated • 359
nm-testing/w4a16_sym_awq-e2e
1B • Updated • 315
nm-testing/w4a16_grouped_quant-e2e
1B • Updated • 325
nm-testing/w4a16_asym_awq-e2e
1B • Updated • 360
nm-testing/w4a16_actorder_weight-e2e
1B • Updated • 406
nm-testing/nvfp4_fp8_mixed-e2e
0.7B • Updated • 382
nm-testing/multiple_modifiers_gptq_awq_disk-e2e
0.9B • Updated • 342
nm-testing/multiple_modifiers_gptq_awq-e2e
0.9B • Updated • 376
nm-testing/model_free_nvfp4a16-e2e
1B • Updated • 207
nm-testing/model_free_fp8-e2e
1B • Updated • 208
nm-testing/kv_cache_gptq_tinyllama-e2e
1B • Updated • 388
nm-testing/kv_cache_fp8-e2e
1B • Updated • 389
nm-testing/int8_dynamic_per_token-e2e
1B • Updated • 290
nm-testing/int8_channel_weight_static_per_tensor_act-e2e
1B • Updated • 416
nm-testing/fp8_weight_only_tensor-e2e
1B • Updated • 288
nm-testing/fp8_weight_only_channel-e2e
1B • Updated • 276
nm-testing/nvfp4_moe-e2e
31B • Updated • 305
nm-testing/fp8_static_per_tensor-e2e
1B • Updated • 291
nm-testing/fp8_dynamic_per_token-e2e
1B • Updated • 276
nm-testing/fp8_block-e2e
1B • Updated • 267
nm-testing/fp4_nvfp4a16-e2e
1B • Updated • 332
nm-testing/fp4_nvfp4-e2e
1B • Updated • 292
nm-testing/fp8_dynamic_moe-e2e
31B • Updated • 349
nm-testing/convert_modelopt_nvfp4-e2e
Text Generation • 8B • Updated • 2.55k
nm-testing/w4a16_rtn_smoke-e2e
1B • Updated • 179
nm-testing/convert_awq_w4a16_asym-e2e
Text Generation • 0.6B • Updated • 364