Hugging Face model directory
nm-testing
NM Testing
554 public models. Explore architecture graphs, discover recent releases, and find your next model.
nm-testing on Hugging Face ↗
Watch nm-testing releases
-
Qwen3-30B-A3B-NVFP4-e2e
↓ 44 downloads♡ 0 likes -
GLM-4.5-Air-0.72B-MTP
↓ 535 downloads♡ 0 likes -
Inkling-Dense-54M-MTP
↓ 161 downloads♡ 0 likes -
GLM-5.2-0.8B-A0.8B-FP8-REAP-15-nonuniform
↓ 34 downloads♡ 0 likes -
Qwen3-30B-A3B-NVFP4-AWQ-e2e
↓ 374 downloads♡ 0 likes -
w8a8_static_asym-e2e
↓ 355 downloads♡ 0 likes -
w8a8_dynamic_asym-e2e
↓ 355 downloads♡ 0 likes -
w4a16_sym_awq-e2e
↓ 344 downloads♡ 0 likes -
w4a16_grouped_quant-e2e
↓ 398 downloads♡ 0 likes -
w4a16_asym_awq-e2e
↓ 391 downloads♡ 0 likes -
w4a16_actorder_weight-e2e
↓ 370 downloads♡ 0 likes -
nvfp4_fp8_mixed-e2e
↓ 475 downloads♡ 0 likes -
multiple_modifiers_gptq_awq_disk-e2e
↓ 337 downloads♡ 0 likes -
multiple_modifiers_gptq_awq-e2e
↓ 373 downloads♡ 0 likes -
kv_cache_gptq_tinyllama-e2e
↓ 375 downloads♡ 0 likes -
kv_cache_fp8-e2e
↓ 483 downloads♡ 0 likes -
int8_channel_weight_static_per_tensor_act-e2e
↓ 434 downloads♡ 0 likes -
fp8_dynamic_moe-e2e
↓ 394 downloads♡ 0 likes -
w4a16_gptq_smoke-e2e
↓ 409 downloads♡ 0 likes -
Qwen3.8-27B-MXFP6A8
↓ 65 downloads♡ 0 likes -
Qwen3-0.6B-MXFP6A8
↓ 178 downloads♡ 0 likes -
Qwen3.6-35B-A3B-NVFP4-REAP10-nonuniform
↓ 78 downloads♡ 0 likes -
model_free_fp8-e2e
↓ 301 downloads♡ 0 likes -
w8a16_grouped_quant-e2e
↓ 355 downloads♡ 0 likes -
nvfp4_moe-e2e
↓ 362 downloads♡ 0 likes -
w4a16_moe-e2e
↓ 316 downloads♡ 0 likes -
qwen36_nvfp4_fp8
↓ 36 downloads♡ 0 likes -
Qwen3.8-27B-NVFP4-FP8
↓ 68 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-w4a16-sym-awq-e2e
↓ 33 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-actorder-none-e2e
↓ 26 downloads♡ 0 likes -
Qwen3-30B-A3B-FP8_DYNAMIC-e2e
↓ 43 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-nvfp4-fp8-mixed-e2e
↓ 51 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-gptq-awq-mixed-e2e
↓ 42 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-FP8_BLOCK-e2e
↓ 47 downloads♡ 0 likes -
w4a16_actorder_group-e2e
↓ 43 downloads♡ 0 likes -
model_free_nvfp4a16-e2e
↓ 357 downloads♡ 0 likes -
int8_dynamic_per_token-e2e
↓ 319 downloads♡ 0 likes -
fp8_weight_only_tensor-e2e
↓ 333 downloads♡ 0 likes -
fp8_weight_only_channel-e2e
↓ 349 downloads♡ 1 like -
fp8_static_per_tensor-e2e
↓ 404 downloads♡ 0 likes -
fp8_dynamic_per_token-e2e
↓ 339 downloads♡ 0 likes -
fp8_block-e2e
↓ 345 downloads♡ 0 likes -
fp4_nvfp4a16-e2e
↓ 359 downloads♡ 0 likes -
fp4_nvfp4-e2e
↓ 344 downloads♡ 0 likes -
convert_modelopt_nvfp4-e2e
↓ 2,263 downloads♡ 0 likes -
convert_fp8_dequant-e2e
↓ 11 downloads♡ 0 likes -
convert_ct_dequant-e2e
↓ 2 downloads♡ 0 likes -
w4a16_rtn_smoke-e2e
↓ 293 downloads♡ 0 likes -
convert_awq_w4a16_asym-e2e
↓ 700 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-W8A8-Static-Asym-e2e
↓ 52 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Asym-e2e
↓ 51 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-W8A16-e2e
↓ 52 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-W8A16_channel-e2e
↓ 46 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-w4a16-asym-awq-e2e
↓ 43 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-W4A16-e2e
↓ 61 downloads♡ 0 likes -
Qwen2.5-0.5B-W4A16_channel-e2e
↓ 9 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-W4A16_channel-e2e
↓ 50 downloads♡ 0 likes -
Qwen2.5-0.5B-actorder-weight-e2e
↓ 24 downloads♡ 0 likes -
TinyLlama-1.1B-Chat-v1.0-actorder-weight-e2e
↓ 46 downloads♡ 0 likes -
Qwen2.5-0.5B-actorder-group-e2e
↓ 27 downloads♡ 0 likes