Updated 2026-09-20 · 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 23.0 M from 2.3 GB
02 gpt2 openai-community · text-generation 140 M ✓ mit 15.4 M from 1.1 GB
03 Qwen3-8B +2 variants Qwen · text-generation 8.2 B 41 K ✓ apache-2.0 12.9 M from 19.7 GB
04 Qwen3-Coder-30B-A3B-Instruct-GGUF +2 variants unsloth · text-generation ✓ apache-2.0 12.7 M from 12.9 GB
05 Qwen2.5-7B-Instruct +1 variant Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 9.7 M from 18.4 GB
06 Qwen2.5-0.5B-Instruct Qwen · text-generation 490 M 33 K ✓ apache-2.0 8.5 M from 1.7 GB
07 Qwen3.6-35B-A3B-NVFP4 nvidia · text-generation 18.7 B ✓ apache-2.0 8.3 M from 29.1 GB
08 Qwen2.5-1.5B-Instruct Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 7.2 M from 4.1 GB
09 Qwen3-4B Qwen · text-generation 4.0 B 41 K ✓ apache-2.0 7.1 M from 10.0 GB
10 OTel-2.0-LLM-31B-IT farbodtavakkoli · text-generation 31.3 B 262 K ✓ apache-2.0 6.9 M from 144.6 GB
11 gpt-oss-20b openai · text-generation 21.5 B 131 K ✓ apache-2.0 6.7 M from 34.0 GB
12 Ornith-1.5-9B-GGUF +1 variant ornith-ai · text-generation ✓ mit 5.8 M from 6.9 GB
13 gpt-oss-120b openai · text-generation 120.4 B 131 K ✓ apache-2.0 5.1 M from 162.1 GB
14 Qwen3-32B +1 variant Qwen · text-generation 32.8 B 41 K ✓ apache-2.0 5.0 M from 77.5 GB
15 Ornith-1.0-9B-GGUF +3 variants deepreinforce-ai · text-generation ✓ mit 4.9 M from 6.7 GB
16 dolphin-2.9.1-yi-1.5-34b dphn · text-generation 34.4 B 8 K ✓ apache-2.0 4.8 M from 81.3 GB
17 Ornith-1.5-35B-A3B-GGUF +1 variant ornith-ai · text-generation ✓ mit 4.6 M from 24.4 GB
18 DeepSeek-V4-Flash-0731 deepseek-ai · text-generation 304.2 B 1.0 M ✓ mit 4.2 M from 229.7 GB
19 Qwen3-4B-Instruct-2507 +1 variant Qwen · text-generation 4.0 B 262 K ✓ apache-2.0 4.0 M from 10.0 GB
20 Qwen3-1.7B Qwen · text-generation 2.0 B 41 K ✓ apache-2.0 3.8 M from 5.3 GB
21 Ornith-1.0-35B-GGUF +4 variants deepreinforce-ai · text-generation ✓ mit 3.8 M from 23.8 GB
22 pythia-160m EleutherAI · text-generation 210 M 2 K ✓ apache-2.0 3.5 M from 0.9 GB
23 Qwen2.5-Coder-7B-Instruct +1 variant Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 2.6 M from 18.4 GB
24 Qwen3-14B-AWQ +1 variant Qwen · text-generation 14.8 B 41 K ✓ apache-2.0 2.6 M from 13.7 GB
25 DeepSeek-V3.2 deepseek-ai · text-generation 685.4 B 164 K ✓ mit 2.4 M from 861.7 GB
Membership and ranking refresh nightly after the snapshot run. VRAM is an estimate for the smallest quantization at 8K context — methodology.