nm-testing AI Models
Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗
- Tracked modelsRepositories from this publisher currently tracked by OpenModelStats.
- 89
- Downloads 30DSum of each tracked model's rolling recent-downloads counter. A sum of repository counters is not a count of unique users.
- 918.6K
- Total downloadsSum of cumulative all-time download counters across tracked repositories.
- 14.1M
- Total likes
- 31
- Gained 7DCombined seven-day cumulative-download gains measured by OpenModelStats.
- 278.5K
Most downloaded
- 1SmolLM-1.7B-Instruct-quantized.w4a16Jul 22, 2026471.4K
- 2tinysmokellama-3.2Jun 12, 2026172K
- 3tinysmokeqwen3Jun 15, 202678K
- 4tinysmokeqwen3moeNov 20, 202525.5K
- 5Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16Feb 24, 202515.7K
- 6Meta-Llama-3-8B-Instruct-nonuniform-testAug 20, 20267,621
- 7qwen3-8b-peagle-speculatorsMay 7, 20267,067
- 8llama2.c-stories15MMar 10, 20257,067
- 9dflash-qwen3-8b-speculatorsApr 15, 20267,000
- 10SpeculatorLlama3-1-8B-Eagle3-converted-0717-quantizedJul 29, 20256,711
Fastest growing
- 1SmolLM-1.7B-Instruct-quantized.w4a16+151.3K in 7D471.4K
- 2tinysmokellama-3.2+54.7K in 7D172K
- 3tinysmokeqwen3+25.7K in 7D78K
- 4tinysmokeqwen3moe+7,684 in 7D25.5K
- 5Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16+4,527 in 7D15.7K
- 6qwen3-8b-peagle-speculators+2,177 in 7D7,067
- 7dflash-qwen3-8b-speculators+2,141 in 7D7,000
- 8SpeculatorLlama3-1-8B-Eagle3-converted-0717-quantized+2,025 in 7D6,711
- 9Speculator-Qwen3-8B-Eagle3-converted-071-quantized+2,011 in 7D6,628
- 10Meta-Llama-3-8B-Instruct-nonuniform-test+1,868 in 7D7,621
Recently updated
- 1Qwen3-30B-A3B-NVFP4-AWQ-e2eOct 8, 2026316
- 2w8a8_static_asym-e2eOct 8, 2026245
- 3w8a8_dynamic_asym-e2eOct 8, 2026264
- 4w8a16_grouped_quant-e2eOct 8, 2026252
- 5w4a16_sym_awq-e2eOct 8, 2026222
- 6w4a16_grouped_quant-e2eOct 8, 2026231
- 7w4a16_asym_awq-e2eOct 8, 2026257
- 8w4a16_actorder_weight-e2eOct 8, 2026262
- 9nvfp4_fp8_mixed-e2eOct 8, 2026265
- 10multiple_modifiers_gptq_awq_disk-e2eOct 8, 2026233
All models
| Model | DL 30D | 7D |
|---|---|---|
| multiple_modifiers_gptq_awq-e2enm-testing/multiple_modifiers_gptq_awq-e2e | 251 | +61 |
| fp8_dynamic_per_token-e2enm-testing/fp8_dynamic_per_token-e2e | 249 | +52 |
| w8a8_static_asym-e2enm-testing/w8a8_static_asym-e2e | 246 | +53 |
| w4a16_rtn_smoke-e2enm-testing/w4a16_rtn_smoke-e2e | 241 | +54 |
| Qwen3-4B-mixed-quant-RTN-wNaMnm-testing/qwen3-4b-mixed-quant-rtn-wnam | 240 | +73 |
| multiple_modifiers_gptq_awq_disk-e2enm-testing/multiple_modifiers_gptq_awq_disk-e2e | 228 | +53 |
| w4a16_grouped_quant-e2enm-testing/w4a16_grouped_quant-e2e | 222 | +53 |
| w4a16_sym_awq-e2enm-testing/w4a16_sym_awq-e2e | 216 | +50 |
| DeepSeek-V2-Lite-W8A8-Dynamic-Per-Tokennm-testing/deepseek-v2-lite-w8a8-dynamic-per-token | 65 | +14 |
| Llama-3.3-70B-Instruct-FP8-dynamicnm-testing/llama-3.3-70b-instruct-fp8-dynamic | 64 | +6 |
| w4a16_actorder_group-e2enm-testing/w4a16_actorder_group-e2e | 48 | +4 |
| Mixtral-8x7B-Instruct-v0.1-W8A16-quantizednm-testing/mixtral-8x7b-instruct-v0.1-w8a16-quantized | 32 | +0 |
| Moonlight-16B-A3B.w4a16nm-testing/moonlight-16b-a3b.w4a16 | 21 | +1 |
| qwen36_nvfp4_fp8nm-testing/qwen36_nvfp4_fp8 | 0 | +0 |