Daily download tracking since 28 Jul 2026
Which open models are actually winning — measured daily, not guessed.
We snapshot downloads, likes and file inventories for the top 1,030 Hugging Face models every night at 04:00 UTC. That history powers trend charts, VRAM estimates and side-by-side comparisons you can't get from the model card.
Catalog downloads · trailing 30d
1.8 B
▲ 2.4% vs previous 30d
last 40 days
25,487
compare pages
0
real outputs
40
days tracked
| # | Model | 30d | Δ 7d | Trend |
|---|---|---|---|---|
| 01 | glm-4-9b-chat-IMat-GGUF | 871 K | ▲ 318.3% | |
| 02 | NVIDIA-Nemotron-3-Nano-4B-BF16 | 1.8 M | ▲ 315.7% | |
| 03 | Llama-3.3-70B-Instruct | 816 K | ▲ 184.0% | |
| 04 | granite-4.1-30b | 486 K | ▲ 174.6% | |
| 05 | Juggernaut-XL-v9 | 593 K | ▲ 165.6% | |
| 06 | Ornith-1.5-397B-GGUF | 740 K | ▲ 160.9% | |
| 07 | Qwen3.8-4B-Distill-GGUF | 445 K | ▲ 154.3% | |
| 08 | FLUX.2-klein-4B-mflux-4bit | 58 K | ▲ 148.7% |
Fresh comparisons
Browse by hardware
For machines
Read-only JSON, no key, 60 req/min. Snapshots also ship as a daily CSV dump.
Collections
Sponsored · GPU cloud
Rent an A100 by the hour
Run 70B models without buying hardware. From $1.29/hr.
Data from the public Hugging Face API, snapshotted daily. VRAM figures are estimates — see /methodology.