nm-testing/fp8_dynamic_moe-e2e
31B • Updated • 343
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
nm-testing/qwen36_nvfp4_fp8
20B • Updated • 257
nm-testing/Mixtral-8x7B-Instruct-v0.1-W8A16-quantized
47B • Updated • 32
nm-testing/Qwen3-Next-80B-A3B-Instruct-NVFP4
46B • Updated • 264 • 2
nm-testing/w4a16_actorder_group-e2e
1B • Updated • 156
nm-testing/llama2.c-stories15M-ultrachat-mixed-uncompressed
24.4M • Updated • 2.32k
nm-testing/Llama-2-7b-hf-gsm8k-quant_w4a16_sym-uncompressed
7B • Updated • 32
nm-testing/Llama-2-7b-hf-gsm8k-gptq_w4a16_sym-uncompressed
7B • Updated • 34
nm-testing/Llama-2-7b-hf-gsm8k-awq_w4a16_sym-uncompressed
7B • Updated • 34
nm-testing/Llama-2-7b-hf-gsm8k-awq_gptq_sym-uncompressed
7B • Updated • 33
nm-testing/Llama-3.2-1B-Instruct-W4A16-uncompressed-mse-hadamard
5B • Updated • 41
nm-testing/llama2.c-stories42M-gsm8k-stacked-uncompressed
58.1M • Updated • 1.13k
nm-testing/llama2.c-stories42M-gsm8k-quantized-only-uncompressed
58.1M • Updated • 2.63k
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Per-Token-uncompressed
1B • Updated • 410
nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A16-G128-uncompressed
1B • Updated • 549
nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-uncompressed
1B • Updated • 411
nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-Dynamic-uncompressed
1B • Updated • 553
nm-testing/llama2.c-stories15M-pruned_50.2of4-uncompressed-tensor_weights_tensor_act_fp8-BitMaskCompressed
22.2M • Updated • 30
nm-testing/llama-3-fp8-2of4-dynamic-uncompressed
8B • Updated • 25
nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-FP8-uncompressed
8B • Updated • 32
nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-quantized.w4a16-uncompressed
2B • Updated • 35
nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned_50.2of4-FP8-uncompressed
1B • Updated • 33
nm-testing/tinyllama-w8a16-dense
1B • Updated • 1.05k
nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change
Text Generation • 1B • Updated • 6.97k
nm-testing/tinyllama-oneshot-w8a8-static-v2
Text Generation • 1B • Updated • 303
nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym
Text Generation • 1B • Updated • 310
nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2
Text Generation • 1B • Updated • 2.67k
nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2-asym
1B • Updated • 117
nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2
Text Generation • 1B • Updated • 2.98k
nm-testing/tinyllama-oneshot-w8a16-per-channel
Text Generation • 1B • Updated • 1.41k