nm-testing/w4a16_moe-e2e
31B • Updated • 872
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
nm-testing/Qwen3-30B-A3B-NVFP4-AWQ-e2e
31B • Updated • 354
nm-testing/w8a8_static_asym-e2e
1B • Updated • 360
nm-testing/w8a8_dynamic_asym-e2e
1B • Updated • 360
nm-testing/w8a16_grouped_quant-e2e
1B • Updated • 343
nm-testing/w4a16_sym_awq-e2e
1B • Updated • 299
nm-testing/w4a16_grouped_quant-e2e
1B • Updated • 308
nm-testing/w4a16_asym_awq-e2e
1B • Updated • 335
nm-testing/w4a16_actorder_weight-e2e
1B • Updated • 374
nm-testing/nvfp4_fp8_mixed-e2e
0.7B • Updated • 349
nm-testing/multiple_modifiers_gptq_awq_disk-e2e
0.9B • Updated • 310
nm-testing/multiple_modifiers_gptq_awq-e2e
0.9B • Updated • 343
nm-testing/model_free_nvfp4a16-e2e
1B • Updated • 190
nm-testing/model_free_fp8-e2e
1B • Updated • 194
nm-testing/kv_cache_gptq_tinyllama-e2e
1B • Updated • 360
nm-testing/kv_cache_fp8-e2e
1B • Updated • 355
nm-testing/int8_dynamic_per_token-e2e
1B • Updated • 255
nm-testing/int8_channel_weight_static_per_tensor_act-e2e
1B • Updated • 370
nm-testing/fp8_weight_only_tensor-e2e
1B • Updated • 255
nm-testing/fp8_weight_only_channel-e2e
1B • Updated • 247
nm-testing/nvfp4_moe-e2e
31B • Updated • 270
nm-testing/fp8_static_per_tensor-e2e
1B • Updated • 249
nm-testing/fp8_dynamic_per_token-e2e
1B • Updated • 246
nm-testing/fp8_block-e2e
1B • Updated • 238
nm-testing/fp4_nvfp4a16-e2e
1B • Updated • 298
nm-testing/fp4_nvfp4-e2e
1B • Updated • 260
nm-testing/fp8_dynamic_moe-e2e
31B • Updated • 306
nm-testing/convert_modelopt_nvfp4-e2e
Text Generation • 8B • Updated • 2.1k
nm-testing/w4a16_rtn_smoke-e2e
1B • Updated • 160
nm-testing/convert_awq_w4a16_asym-e2e
Text Generation • 0.6B • Updated • 324