Updated 2026-08-06 · 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.

#ModelParamsContextCommercial use30dMin VRAM
01 Qwen3-0.6B Qwen · text-generation 750 M 41 K ✓ apache-2.0 29.7 M from 2.3 GB
02 Qwen3-8B Qwen · text-generation 8.2 B 41 K ✓ apache-2.0 16.3 M from 19.7 GB
03 Qwen2.5-1.5B-Instruct Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 14.0 M from 4.1 GB
04 gpt2 openai-community · text-generation 140 M ✓ mit 13.7 M from 1.1 GB
05 Qwen2.5-7B-Instruct Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 12.1 M from 18.4 GB
06 Qwen3.6-35B-A3B-NVFP4 nvidia · text-generation 18.7 B ✓ apache-2.0 11.3 M from 29.1 GB
07 DeepSeek-R1 deepseek-ai · text-generation 684.5 B 164 K ✓ mit 9.9 M from 860.6 GB
08 gpt-oss-20b openai · text-generation 21.5 B 131 K ✓ apache-2.0 8.6 M from 34.0 GB
09 Qwen3-32B Qwen · text-generation 32.8 B 41 K ✓ apache-2.0 8.3 M from 77.5 GB
10 Qwen3-1.7B Qwen · text-generation 2.0 B 41 K ✓ apache-2.0 7.8 M from 5.3 GB
11 Qwen2.5-0.5B-Instruct Qwen · text-generation 490 M 33 K ✓ apache-2.0 6.6 M from 1.7 GB
12 Ornith-1.0-9B-GGUF ornith-ai · text-generation ✓ mit 4.9 M from 6.7 GB
13 Ornith-1.0-9B-GGUF deepreinforce-ai · text-generation ✓ mit 4.9 M from 6.7 GB
14 Qwen3-Coder-30B-A3B-Instruct-GGUF unsloth · text-generation ✓ apache-2.0 4.7 M from 12.9 GB
15 OTel-LLM-E4B-IT farbodtavakkoli · text-generation ✓ apache-2.0 4.7 M
16 Qwen2.5-7B-Instruct-AWQ Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 4.6 M from 7.8 GB
17 dolphin-2.9.1-yi-1.5-34b dphn · text-generation 34.4 B 8 K ✓ apache-2.0 4.6 M from 81.3 GB
18 Qwen3-4B Qwen · text-generation 4.0 B 41 K ✓ apache-2.0 4.6 M from 10.0 GB
19 gpt-oss-120b openai · text-generation 120.4 B 131 K ✓ apache-2.0 4.2 M from 162.1 GB
20 granite-4.1-8b ibm-granite · text-generation 8.8 B 131 K ✓ apache-2.0 4.2 M from 21.2 GB
21 Ornith-1.0-35B-GGUF ornith-ai · text-generation ✓ mit 3.8 M from 23.8 GB
22 Ornith-1.0-35B-GGUF deepreinforce-ai · text-generation ✓ mit 3.8 M from 23.8 GB
23 Qwen2.5-14B-Instruct Qwen · text-generation 14.8 B 33 K ✓ apache-2.0 3.3 M from 35.2 GB
24 OTel-2.0-LLM-31B-IT farbodtavakkoli · text-generation 32.1 B 262 K ✓ apache-2.0 3.3 M from 76.0 GB
25 Qwen3-4B-Instruct-2507 Qwen · text-generation 4.0 B 262 K ✓ apache-2.0 3.2 M from 10.0 GB
Membership and ranking refresh nightly after the snapshot run. VRAM is an estimate for the smallest quantization at 8K context — methodology.