Updated 2026-11-10 · ranked by real download data
Commercial-use text models
Ranked nightly from our download snapshots of the Hugging Face catalog. Every entry shows its licence and what hardware it realistically needs.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 01 | gpt2 | 140 M | — | ✓ mit | 31.8 M | from 1.1 GB |
| 02 | Qwen3-0.6B +1 variant | 750 M | 41 K | ✓ apache-2.0 | 20.7 M | from 2.3 GB |
| 03 | Qwen3-14B +1 variant | 14.8 B | 41 K | ✓ apache-2.0 | 12.9 M | from 35.2 GB |
| 04 | DeepSeek-V3.2 | 685.4 B | 164 K | ✓ mit | 7.6 M | from 861.7 GB |
| 05 | Qwen3-8B +2 variants | 8.2 B | 41 K | ✓ apache-2.0 | 6.8 M | from 19.7 GB |
| 06 | Qwen2.5-7B-Instruct +2 variants | 7.6 B | 33 K | ✓ apache-2.0 | 6.0 M | from 18.4 GB |
| 07 | gpt-oss-20b +1 variant | 21.5 B | 131 K | ✓ apache-2.0 | 5.8 M | from 34.0 GB |
| 08 | Ornith-1.5-9B-GGUF +1 variant | — | — | ✓ mit | 5.8 M | from 6.9 GB |
| 09 | Qwen2.5-1.5B-Instruct | 1.5 B | 33 K | ✓ apache-2.0 | 5.0 M | from 4.1 GB |
| 10 | Ornith-1.0-9B-GGUF +3 variants | — | — | ✓ mit | 4.9 M | from 6.7 GB |
| 11 | dolphin-2.9.1-yi-1.5-34b | 34.4 B | 8 K | ✓ apache-2.0 | 4.8 M | from 81.3 GB |
| 12 | Qwen2.5-0.5B-Instruct | 490 M | 33 K | ✓ apache-2.0 | 4.5 M | from 1.7 GB |
| 13 | Ornith-1.5-35B-A3B-GGUF +1 variant | — | — | ✓ mit | 4.2 M | from 24.4 GB |
| 14 | Qwen3-4B +1 variant | 4.0 B | 41 K | ✓ apache-2.0 | 4.0 M | from 10.0 GB |
| 15 | Qwen3.6-35B-A3B-NVFP4 | 18.7 B | — | ✓ apache-2.0 | 4.0 M | from 29.1 GB |
| 16 | Ornith-1.0-35B-GGUF +4 variants | — | — | ✓ mit | 3.8 M | from 23.8 GB |
| 17 | Qwen3-1.7B | 2.0 B | 41 K | ✓ apache-2.0 | 3.7 M | from 5.3 GB |
| 18 | pythia-160m | 210 M | 2 K | ✓ apache-2.0 | 3.5 M | from 0.9 GB |
| 19 | DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF | 763.2 B | — | ✓ mit | 3.3 M | from 116.1 GB |
| 20 | OTel-2.0-Decision-26B-A4B-4bit | 25.8 B | — | ✓ apache-2.0 | 3.2 M | from 22.8 GB |
| 21 | Qwen3-32B | 32.8 B | 41 K | ✓ apache-2.0 | 3.0 M | from 77.5 GB |
| 22 | DeepSeek-V4-Flash-0731 | 304.2 B | 1.0 M | ✓ mit | 2.7 M | from 229.7 GB |
| 23 | Qwen3-4B-Instruct-2507 +1 variant | 4.0 B | 262 K | ✓ apache-2.0 | 2.6 M | from 10.0 GB |
| 24 | SmolLM2-135M | 130 M | 8 K | ✓ apache-2.0 | 2.5 M | from 0.8 GB |
| 25 | Qwen3.8-27B-Uncensored-GGUF | — | — | ✓ apache-2.0 | 2.5 M | from 1.5 GB |
Membership and ranking refresh nightly after the snapshot run. VRAM is an estimate for the smallest quantization at 8K context — methodology.