nm-testing/Qwen3-30B-A3B-NVFP4-AWQ-e2e
31B • Updated • 418
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
nm-testing/w8a8_static_asym-e2e
1B • Updated • 293
nm-testing/tinyllama-w8a16-dense
1B • Updated • 1.09k
nm-testing/w8a8_dynamic_asym-e2e
1B • Updated • 320
nm-testing/w8a16_grouped_quant-e2e
1B • Updated • 317 • 1
nm-testing/w4a16_sym_awq-e2e
1B • Updated • 262
nm-testing/w4a16_grouped_quant-e2e
1B • Updated • 282
nm-testing/w4a16_asym_awq-e2e
1B • Updated • 313
nm-testing/w4a16_actorder_weight-e2e
1B • Updated • 343
nm-testing/nvfp4_fp8_mixed-e2e
0.7B • Updated • 325
nm-testing/multiple_modifiers_gptq_awq_disk-e2e
0.9B • Updated • 286
nm-testing/multiple_modifiers_gptq_awq-e2e
0.9B • Updated • 313
nm-testing/model_free_nvfp4a16-e2e
1B • Updated • 216
nm-testing/model_free_fp8-e2e
1B • Updated • 228
nm-testing/kv_cache_gptq_tinyllama-e2e
1B • Updated • 376
nm-testing/kv_cache_fp8-e2e
1B • Updated • 393
nm-testing/int8_dynamic_per_token-e2e
1B • Updated • 277
nm-testing/int8_channel_weight_static_per_tensor_act-e2e
1B • Updated • 438 • 1
nm-testing/fp8_weight_only_tensor-e2e
1B • Updated • 253
nm-testing/fp8_weight_only_channel-e2e
1B • Updated • 267 • 1
nm-testing/fp8_static_per_tensor-e2e
1B • Updated • 336
nm-testing/nvfp4_moe-e2e
31B • Updated • 375
nm-testing/fp8_dynamic_per_token-e2e
1B • Updated • 245
nm-testing/fp8_block-e2e
1B • Updated • 269
nm-testing/fp4_nvfp4a16-e2e
1B • Updated • 265
nm-testing/fp4_nvfp4-e2e
1B • Updated • 303
nm-testing/convert_modelopt_nvfp4-e2e
Text Generation • 8B • Updated • 2.47k
nm-testing/w4a16_rtn_smoke-e2e
1B • Updated • 245
nm-testing/w4a16_gptq_smoke-e2e
1B • Updated • 430
nm-testing/convert_awq_w4a16_asym-e2e
Text Generation • 0.6B • Updated • 404