AImodelsComparison.com 1,213 open · 210 API
Menu
Models Best of Trending Can I run it? Methodology MCP server About
1,423 models · 1,213 open weights · 210 API-only · refreshed nightly

Text generation models

Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

Type
All 1,423 Open weights (self-host) 1,213 API-only 210
Task
All text-generation 735 text-to-image 165 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 text-to-speech 23 token-classification 22 summarization 9 audio-classification 9 image-segmentation 9 object-detection 7 audio-text-to-text 1 any-to-any 1
Runs on
Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB
Licence
Size
$
735 models
#ModelParamsContextCommercial use30dMin VRAM
101 GLM-5.3-Flash-GGUF unsloth · text-generation Open weights 321.3 B — ✓ mit 818 K from 102.9 GB
102 Ornith-1.0-9B ornith-ai · text-generation Open weights <0.1 M — ✓ mit 814 K from 21.2 GB
103 gemma-2-9b-it-AWQ-INT4 hugging-quants · text-generation Open weights 9.2 B 8 K ⚠ gemma 803 K from 8.7 GB
104 Qwen2.5-32B-Instruct Qwen · text-generation Open weights 32.8 B 33 K ✓ apache-2.0 775 K from 77.5 GB
105 Qwen2.5-Coder-7B-Instruct-AWQ Qwen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 769 K from 7.8 GB
106 Qwen2.5-7B-Instruct-GGUF Qwen · text-generation Open weights 7.0 B 33 K ✓ apache-2.0 738 K from 4.9 GB
107 NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 nvidia · text-generation Open weights 18.2 B 262 K other 733 K from 24.5 GB
108 pythia-70m-deduped EleutherAI · text-generation Open weights 100 M 2 K ✓ apache-2.0 729 K from 0.7 GB
109 OTel-2.0-LLM-31B-IT farbodtavakkoli · text-generation Open weights 31.3 B 262 K ✓ apache-2.0 720 K from 144.6 GB
110 Qwen3-4B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 719 K from 3.2 GB
111 Underdog-Saluki-27B-1.0 ConwayResearch · text-generation Open weights 27.0 B — ✗ cc-by-nc-4.0 710 K from 5.2 GB
112 Laguna-XS-2.1 poolside · text-generation Open weights 33.4 B 262 K openmdw-1.1 700 K from 79.1 GB
113 gemma-4-31B-it-qat-NVFP4-Blackwell melcheikh · text-generation Open weights 31.0 B — ✓ apache-2.0 699 K from 27.6 GB
114 Qwen2.5-14B-Instruct Qwen · text-generation Open weights 14.8 B 33 K ✓ apache-2.0 679 K from 35.2 GB
115 Qwen2.5-32B-Instruct-GGUF bartowski · text-generation Open weights 32.0 B 33 K ✓ apache-2.0 676 K from 15.2 GB
116 Ornith-1.0-397B-FP8 deepreinforce-ai · text-generation Open weights 397.0 B — ✓ mit 673 K from 505.7 GB
117 Diplodocus-preview-GGUF OsaurusAI · text-generation Open weights — — ✓ apache-2.0 663 K from 0.5 GB
118 Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata Maximilian228 · text-generation Open weights 180.0 B — other 657 K from 83.8 GB
119 LFM2.5-24B-A2B-Uncensored-GGUF AtomicChat · text-generation Open weights 24.0 B 131 K other 639 K from 4.1 GB
120 MiniCPM5-2B-DSpark openbmb · text-generation Open weights 324 M 131 K ✓ apache-2.0 631 K from 1.3 GB
121 Qwen3-1.7B-Base Qwen · text-generation Open weights 1.7 B 33 K ✓ apache-2.0 629 K from 4.5 GB
122 gpt-oss-20b-GGUF unsloth · text-generation Open weights — 131 K ✓ apache-2.0 624 K from 13.1 GB
123 MiniCPM-SALA-AWQ-8bit cyankiwi · text-generation Open weights 3.1 B 524 K ✓ apache-2.0 621 K from 12.7 GB
124 Qwen3-0.6B-Base Qwen · text-generation Open weights 600 M 33 K ✓ apache-2.0 612 K from 1.9 GB
125 deepseek-v4-gguf antirez · text-generation Open weights — — ✓ mit 606 K from 4.7 GB
126 Spark-X2.6-4B-GGUF XHToken · text-generation Open weights 4.0 B — ✓ apache-2.0 606 K from 5.0 GB
127 DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai · text-generation Open weights 1.8 B 131 K ✓ mit 600 K from 4.7 GB
128 bloomz-560m bigscience · text-generation Open weights 560 M — ⚠ bigscience-bloom-rail-1.0 599 K from 1.8 GB
129 Ornith-1.5-122B-GGUF unsloth · text-generation Open weights 122.0 B — ✓ mit 593 K from 63.2 GB
130 Qwen3.8-27B-Defiance-Uncensored-MTP-GGUF ttindall · text-generation Open weights 27.0 B — ✓ apache-2.0 590 K from 5.5 GB
131 Sage-A1.5-Q4_K_M-GGUF InternScience · text-generation Open weights — — ✓ apache-2.0 586 K from 1.5 GB
132 Qwen3.8-4B-Distill-GGUF empero-ai · text-generation Open weights — — ✓ apache-2.0 579 K from 3.6 GB
133 Laguna-S-2.1 poolside · text-generation Open weights 117.6 B 1.0 M openmdw-1.1 575 K from 276.8 GB
134 Spark-X2.5-4B-Heretic-jp-gguf soyaakinohara · text-generation Open weights 4.0 B — ✓ apache-2.0 556 K from 4.0 GB
135 Qwen3-8B-Base Qwen · text-generation Open weights 8.2 B 33 K ✓ apache-2.0 550 K from 19.7 GB
136 Qwen2.5-Coder-32B-Instruct Qwen · text-generation Open weights Also via API 32.8 B 33 K ✓ apache-2.0 548 K from 77.5 GB
137 Qwen2.5-1.5B Qwen · text-generation Open weights 1.5 B 131 K ✓ apache-2.0 541 K from 4.1 GB
138 Qwen3.8-9B-Distill-GGUF empero-ai · text-generation Open weights — — ✓ apache-2.0 540 K from 6.9 GB
139 Llama-3.2-3B-Instruct unsloth · text-generation Open weights 3.2 B 131 K ⚠ llama3.2 536 K from 8.0 GB
140 Qwen3.8-27B-OBLITERATED OBLITERATUS · text-generation Open weights 27.8 B — ✓ apache-2.0 533 K from 5.7 GB
141 Qwen3-4B-GGUF unsloth · text-generation Open weights — 41 K ✓ apache-2.0 532 K from 2.3 GB
142 granite-4.1-3b ibm-granite · text-generation Open weights 3.4 B 131 K ✓ apache-2.0 524 K from 8.5 GB
143 japanese-gpt-neox-small rinna · text-generation Open weights 200 M 2 K ✓ mit 520 K from 1.3 GB
144 Ornith-1.5-9B ornith-ai · text-generation Open weights 9.7 B — ✓ mit 518 K from 23.2 GB
145 llama-3.3-70b-instruct-awq casperhansen · text-generation Open weights 70.6 B 131 K ⚠ llama3.3 511 K from 54.8 GB
146 Qwen3.8-2B-Distill-GGUF empero-ai · text-generation Open weights — — ✓ apache-2.0 510 K from 1.9 GB
147 POCKET-35B-GGUF FINAL-Bench · text-generation Open weights 35.0 B — ✓ apache-2.0 504 K from 14.8 GB
148 Qwen2.5-1.5B-Instruct-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 494 K from 1.3 GB
149 Qwen3.6-35B-A3B-abliterated-v4 Bahushruth · text-generation Open weights 34.7 B 262 K ✓ apache-2.0 494 K from 82.0 GB
150 DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF Abiray · text-generation Open weights 763.2 B — ✓ mit 490 K from 116.1 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.