nm-testing AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
69
Downloads 30D
1.8M
Total downloads
12.6M
Total likes
25
Gained 7D

Most downloaded

  1. 1SmolLM-1.7B-Instruct-quantized.w4a16Jul 22, 20261M
  2. 2tinysmokellama-3.2Jun 12, 2026135.7K
  3. 3Llama3_2_1B_speculator.eagle3Nov 15, 202598.7K
  4. 4Qwen3-VL-8B-Instruct-NVFP4Oct 17, 202563.6K
  5. 5Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16Feb 24, 202559K
  6. 6tinysmokeqwen3Jun 15, 202648.3K
  7. 7tinyllama-oneshot-w8w8-test-static-shape-changeAug 20, 202636.5K
  8. 8Llama-3.2-1B-Instruct-FP8-KVNov 1, 202422.9K
  9. 9Meta-Llama-3-8B-Instruct-nonuniform-testAug 20, 202621K
  10. 10qwen3-8b-peagle-speculatorsMay 7, 202618.4K

Recently updated

  1. 1w8a8_static_asym-e2eAug 24, 2026405
  2. 2w8a8_dynamic_asym-e2eAug 24, 2026403
  3. 3w8a16_grouped_quant-e2eAug 24, 2026378
  4. 4w4a16_sym_awq-e2eAug 24, 2026336
  5. 5w4a16_grouped_quant-e2eAug 24, 2026337
  6. 6Qwen3-30B-A3B-NVFP4-AWQ-e2eAug 24, 2026388
  7. 7w4a16_asym_awq-e2eAug 24, 2026365
  8. 8w4a16_actorder_weight-e2eAug 24, 2026404
  9. 9w4a16_actorder_group-e2eAug 24, 2026404
  10. 10nvfp4_fp8_mixed-e2eAug 24, 2026388

All models

All tracked models published by nm-testing
ModelDL 30D7D
Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16nm-testing/speculator-qwen3-8b-eagle3-converted-071-quantized-w4a165,912
DeepSeek-V2-Lite-W8A8-Dynamic-Per-Tokennm-testing/deepseek-v2-lite-w8a8-dynamic-per-token5,741
asym-w8w8-int8-static-per-tensor-tiny-llamanm-testing/asym-w8w8-int8-static-per-tensor-tiny-llama5,186
Llama-3.2-1B-Instruct-quip-w4a16nm-testing/llama-3.2-1b-instruct-quip-w4a165,051
Llama-3.2-1B-Instruct-spinquantR1R2R4-w4a16nm-testing/llama-3.2-1b-instruct-spinquantr1r2r4-w4a165,022
pixtral-12b-FP8-dynamicnm-testing/pixtral-12b-fp8-dynamic4,941
TinyLlama-1.1B-Chat-v1.0-kvcache-fp8-tensornm-testing/tinyllama-1.1b-chat-v1.0-kvcache-fp8-tensor4,925
TinyLlama-1.1B-Chat-v1.0-MXFP4nm-testing/tinyllama-1.1b-chat-v1.0-mxfp44,875
TinyLlama-1.1B-Chat-v1.0-kvcache-fp8-attn_headnm-testing/tinyllama-1.1b-chat-v1.0-kvcache-fp8-attn_head4,604
Qwen2-1.5B-Instruct-FP8W8nm-testing/qwen2-1.5b-instruct-fp8w84,429
Qwen3-30B-A3B-FP8-blocknm-testing/qwen3-30b-a3b-fp8-block4,342
Qwen3-30B-A3B-Fp8-v1nm-testing/qwen3-30b-a3b-fp8-v14,189
Llama-3.2-1B-Instruct-quipv16-nvfp4nm-testing/llama-3.2-1b-instruct-quipv16-nvfp43,660
tiny-testing-random-weightsnm-testing/tiny-testing-random-weights3,437
llama2.c-stories42M-gsm8k-quantized-only-compressednm-testing/llama2.c-stories42m-gsm8k-quantized-only-compressed3,001
llama2.c-stories42M-gsm8k-quantized-only-uncompressednm-testing/llama2.c-stories42m-gsm8k-quantized-only-uncompressed2,993
llama2.c-stories15M-ultrachat-mixed-uncompressednm-testing/llama2.c-stories15m-ultrachat-mixed-uncompressed2,663
tinyllama-w4a16-compressednm-testing/tinyllama-w4a16-compressed2,166
convert_modelopt_nvfp4-e2enm-testing/convert_modelopt_nvfp4-e2e2,045
Llama-3.3-70B-Instruct-FP8-dynamicnm-testing/llama-3.3-70b-instruct-fp8-dynamic2,005
Qwen3-4B-mixed-quant-RTN-wNaMnm-testing/qwen3-4b-mixed-quant-rtn-wnam1,971
Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Testnm-testing/meta-llama-3-8b-instruct-w8-channel-a8-dynamic-asym-per-token-test1,970
llama2.c-stories15M-ultrachat-mixed-compressednm-testing/llama2.c-stories15m-ultrachat-mixed-compressed1,814
Meta-Llama-3-70B-Instruct-FBGEMM-nonuniformnm-testing/meta-llama-3-70b-instruct-fbgemm-nonuniform1,782
tinyllama-w8a8-compressednm-testing/tinyllama-w8a8-compressed1,715