OpenModelStats

nm-testing AI Models

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

Tracked models
89
Downloads 30D
918.6K
Total downloads
14.1M
Total likes
31
Gained 7D
278.5K

Most downloaded

  1. 1SmolLM-1.7B-Instruct-quantized.w4a16Jul 22, 2026486.4K
  2. 2tinysmokellama-3.2Jun 12, 2026176.4K
  3. 3tinysmokeqwen3Jun 15, 202680K
  4. 4tinysmokeqwen3moeNov 20, 202528.2K
  5. 5Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16Feb 24, 202516.2K
  6. 6llama2.c-stories15MMar 10, 20257,829
  7. 7Meta-Llama-3-8B-Instruct-nonuniform-testAug 20, 20267,815
  8. 8qwen3-8b-peagle-speculatorsMay 7, 20267,431
  9. 9dflash-qwen3-8b-speculatorsApr 15, 20267,353
  10. 10SpeculatorLlama3-1-8B-Eagle3-converted-0717-quantizedJul 29, 20257,030

Fastest growing

  1. 1SmolLM-1.7B-Instruct-quantized.w4a16+151.3K in 7D486.4K
  2. 2tinysmokellama-3.2+54.7K in 7D176.4K
  3. 3tinysmokeqwen3+25.7K in 7D80K
  4. 4tinysmokeqwen3moe+7,684 in 7D28.2K
  5. 5Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16+4,527 in 7D16.2K
  6. 6qwen3-8b-peagle-speculators+2,177 in 7D7,431
  7. 7dflash-qwen3-8b-speculators+2,141 in 7D7,353
  8. 8SpeculatorLlama3-1-8B-Eagle3-converted-0717-quantized+2,025 in 7D7,030
  9. 9Speculator-Qwen3-8B-Eagle3-converted-071-quantized+2,011 in 7D6,937
  10. 10Meta-Llama-3-8B-Instruct-nonuniform-test+1,868 in 7D7,815

Recently updated

  1. 1Qwen3-30B-A3B-NVFP4-AWQ-e2eOct 8, 2026315
  2. 2w8a8_static_asym-e2eOct 8, 2026247
  3. 3w8a8_dynamic_asym-e2eOct 8, 2026265
  4. 4w8a16_grouped_quant-e2eOct 8, 2026254
  5. 5w4a16_sym_awq-e2eOct 8, 2026224
  6. 6w4a16_grouped_quant-e2eOct 8, 2026230
  7. 7w4a16_asym_awq-e2eOct 8, 2026258
  8. 8w4a16_actorder_weight-e2eOct 8, 2026263
  9. 9nvfp4_fp8_mixed-e2eOct 8, 2026264
  10. 10multiple_modifiers_gptq_awq_disk-e2eOct 8, 2026234

All models

All tracked models published by nm-testing
ModelDL 30D7D
SmolLM-1.7B-Instruct-quantized.w4a16nm-testing/smollm-1.7b-instruct-quantized.w4a16520.7K+151.3K
tinysmokellama-3.2nm-testing/tinysmokellama-3.2177.8K+54.7K
tinysmokeqwen3nm-testing/tinysmokeqwen380K+25.7K
tinysmokeqwen3moenm-testing/tinysmokeqwen3moe28.5K+7,684
Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16nm-testing/qwen1.5-moe-a2.7b-chat-quantized.w4a1617K+4,527
Meta-Llama-3-8B-Instruct-nonuniform-testnm-testing/meta-llama-3-8b-instruct-nonuniform-test8,014+1,868
qwen3-8b-peagle-speculatorsnm-testing/qwen3-8b-peagle-speculators7,805+2,177
dflash-qwen3-8b-speculatorsnm-testing/dflash-qwen3-8b-speculators7,702+2,141
SpeculatorLlama3-1-8B-Eagle3-converted-0717-quantizednm-testing/speculatorllama3-1-8b-eagle3-converted-0717-quantized7,344+2,025
Speculator-Qwen3-8B-Eagle3-converted-071-quantizednm-testing/speculator-qwen3-8b-eagle3-converted-071-quantized7,257+2,011
llama2.c-stories15Mnm-testing/llama2.c-stories15m6,883+1,596
tinysmokeqwen3moe-W4A16-first-only-CTstablenm-testing/tinysmokeqwen3moe-w4a16-first-only-ctstable6,601+1,827
Llama-3.2-1B-Instruct-FP8-KVnm-testing/llama-3.2-1b-instruct-fp8-kv5,537+1,514
tiny-testing-random-weightsnm-testing/tiny-testing-random-weights4,901+897
tinyllama-oneshot-w4a16-channel-v2nm-testing/tinyllama-oneshot-w4a16-channel-v24,867+1,273
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-test4,293+867
tinyllama-oneshot-w8w8-test-static-shape-changenm-testing/tinyllama-oneshot-w8w8-test-static-shape-change4,031+1,144
Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16nm-testing/speculator-qwen3-8b-eagle3-converted-071-quantized-w4a163,347+864
tinyllama-oneshot-w4a16-group128-v2nm-testing/tinyllama-oneshot-w4a16-group128-v23,158+931
convert_modelopt_nvfp4-e2enm-testing/convert_modelopt_nvfp4-e2e2,694+690
llama2.c-stories42M-gsm8k-quantized-only-uncompressednm-testing/llama2.c-stories42m-gsm8k-quantized-only-uncompressed2,536+733
TinyLlama-1.1B-Chat-v1.0-NVFP4nm-testing/tinyllama-1.1b-chat-v1.0-nvfp42,383+558
tinyllama-w4a16-compressednm-testing/tinyllama-w4a16-compressed2,292+556
llama2.c-stories15M-ultrachat-mixed-uncompressednm-testing/llama2.c-stories15m-ultrachat-mixed-uncompressed2,200+588
llama2.c-stories42M-gsm8k-quantized-only-compressednm-testing/llama2.c-stories42m-gsm8k-quantized-only-compressed2,148+641