nm-testing/Qwen3-8B-W8A8-INT8
8B • Updated
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
nm-testing/w8a8_static_asym-e2e
1B • Updated • 388
nm-testing/w8a8_dynamic_asym-e2e
1B • Updated • 414
nm-testing/w8a16_grouped_quant-e2e
1B • Updated • 422
nm-testing/w4a16_sym_awq-e2e
1B • Updated • 350 • 1
nm-testing/w4a16_grouped_quant-e2e
1B • Updated • 372
nm-testing/w4a16_asym_awq-e2e
1B • Updated • 398
nm-testing/w4a16_actorder_weight-e2e
1B • Updated • 385
nm-testing/w4a16_actorder_group-e2e
1B • Updated • 401
nm-testing/nvfp4_fp8_mixed-e2e
0.8B • Updated • 394
nm-testing/multiple_modifiers_gptq_awq_disk-e2e
0.9B • Updated • 173
nm-testing/multiple_modifiers_gptq_awq-e2e
0.9B • Updated • 425
nm-testing/model_free_nvfp4a16-e2e
0.7B • Updated
nm-testing/kv_cache_gptq_tinyllama-e2e
1B • Updated • 410
nm-testing/kv_cache_fp8-e2e
1B • Updated • 394 • 1
nm-testing/int8_dynamic_per_token-e2e
1B • Updated • 277
nm-testing/int8_channel_weight_static_per_tensor_act-e2e
1B • Updated • 394
nm-testing/fp8_weight_only_tensor-e2e
1B • Updated • 302
nm-testing/fp8_weight_only_channel-e2e
1B • Updated • 278
nm-testing/fp8_static_per_tensor-e2e
1B • Updated • 313 • 1
nm-testing/fp8_dynamic_per_token-e2e
1B • Updated • 270
nm-testing/fp8_block-e2e
1B • Updated • 261
nm-testing/fp4_nvfp4a16-e2e
0.7B • Updated • 285
nm-testing/fp4_nvfp4-e2e
0.7B • Updated • 330
nm-testing/convert_modelopt_nvfp4-e2e
Text Generation • 5B • Updated
nm-testing/convert_ct_dequant-e2e
Text Generation • 1B • Updated • 14
nm-testing/convert_awq_w4a16_asym-e2e
Text Generation • 0.6B • Updated • 12
nm-testing/model_free_fp8-e2e
1B • Updated
nm-testing/convert_fp8_dequant-e2e
Text Generation • 4B • Updated
nm-testing/Qwen3-30B-A3B-NVFP4-AWQ-e2e
17B • Updated • 278 • 1