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
251 Qwen3-14B-FP8 Qwen · text-generation Open weights 14.8 B 41 K ✓ apache-2.0 277 K from 20.7 GB
252 llm-jp-4-33b-thinking-gguf llm-jp · text-generation Open weights 33.0 B — ✓ apache-2.0 277 K from 27.6 GB
253 Qwen2-7B-Instruct Qwen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 276 K from 18.4 GB
254 phi-4 microsoft · text-generation Open weights Also via API 14.7 B 16 K ✓ mit 276 K from 34.9 GB
255 LFM2.5-230M-Base LiquidAI · text-generation Open weights 230 M 128 K other 275 K from 1.0 GB
256 Qwen3.8-27B-NVFP4-MTP-GGUF esatapedico · text-generation Open weights 27.0 B — ✓ apache-2.0 275 K from 41.0 GB
257 Ternary-Bonsai-27B-gguf prism-ml · text-generation Open weights — — ✓ apache-2.0 274 K from 1.2 GB
258 Ornith-1.5-122B-NVFP4 ornith-ai · text-generation Open weights 122.0 B — ✓ mit 274 K from 104.2 GB
259 LFM2.5-24B-A2B-GGUF LiquidAI · text-generation Open weights 24.0 B 131 K other 273 K from 19.0 GB
260 GLM-4.7-Flash-AWQ QuantTrio · text-generation Open weights 31.2 B 203 K ✓ mit 272 K from 26.9 GB
261 Llama-3.2-3B meta-llama · text-generation · gated Open weights 3.2 B — ⚠ llama3.2 269 K from 8.0 GB
262 SmolLM2-1.7B-Instruct HuggingFaceTB · text-generation Open weights 1.7 B 8 K ✓ apache-2.0 267 K from 4.5 GB
263 taardis-27b-full-ternary CodeMasterCody3D · text-generation Open weights 27.0 B — ✓ apache-2.0 267 K from 12.4 GB
264 Kimi-K3-DSpark RadixArk · text-generation Open weights 2.3 B 1.0 M unknown 266 K from 5.8 GB
265 Qwen3-30B-A3B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 265 K from 20.9 GB
266 Ornith-1.5-9B-MLX-4bit ornith-ai · text-generation Open weights 9.0 B — unknown 265 K from 7.4 GB
267 Qwen2.5-Coder-7B-Instruct-4bit mlx-community · text-generation Open weights 1.2 B 33 K ✓ apache-2.0 264 K from 5.4 GB
268 Ornith-1.5-122B ornith-ai · text-generation Open weights 125.1 B — ✓ mit 262 K from 294.5 GB
269 Qwen3.8-27B-NVFP4 nvidia · text-generation Open weights 27.0 B — ✓ apache-2.0 260 K from 28.7 GB
270 TwIL-LM3 webAI-Official · text-generation Open weights 3.1 B 66 K other 260 K from 3.1 GB
271 gpt-neox-20b EleutherAI · text-generation Open weights 20.7 B 2 K ✓ apache-2.0 259 K from 49.0 GB
272 DeepSeek-V3.1 deepseek-ai · text-generation Open weights Also via API 684.5 B 164 K ✓ mit 258 K from 860.6 GB
273 LFM2.5-1.2B-Instruct-GGUF LiquidAI · text-generation Open weights 1.2 B 128 K other 257 K from 1.4 GB
274 Kwaipilot_KAT-Coder-V2.5-Dev-GGUF bartowski · text-generation Open weights — — ✓ apache-2.0 257 K from 11.3 GB
275 shieldgemma-9b google · text-generation · gated Open weights 9.2 B — ⚠ gemma 256 K from 22.2 GB
276 Llama-3.2-3B-Instruct-GGUF unsloth · text-generation Open weights — 131 K ⚠ llama3.2 253 K from 2.0 GB
277 Qwen2.5-72B-Instruct-AWQ Qwen · text-generation Open weights 73.0 B 33 K other 252 K from 57.2 GB
278 droplychee-1.0-27b droplychee · text-generation Open weights 27.8 B — ✓ apache-2.0 252 K from 65.8 GB
279 qwen3.8-flash-next-gguf antirez · text-generation Open weights 180.0 B — other 251 K from 189.4 GB
280 Spark-X2.5-1.7B-GGUF XHToken · text-generation Open weights 1.7 B — ✓ apache-2.0 251 K from 2.0 GB
281 Ling-3.0-tiny-GGUF bloomer010 · text-generation Open weights — 131 K ✓ mit 248 K from 2.4 GB
282 Hy3-GGUF vcruz305 · text-generation Open weights — — ✓ apache-2.0 248 K from 52.9 GB
283 Ling-3.0-flash-GGUF AtomicChat · text-generation Open weights 127.5 B 262 K ✓ mit 247 K from 55.2 GB
284 Kimi-K2-Thinking-NVFP4 nvidia · text-generation Open weights 519.1 B 262 K other 245 K from 732.0 GB
285 DeepSeek-V4-Flash-GGUF bartowski · text-generation Open weights — — ✓ mit 245 K from 44.1 GB
286 OTel-LLM-8B-A1B-IT farbodtavakkoli · text-generation Open weights — 128 K ✓ apache-2.0 245 K —
287 h2ovl-mississippi-800m h2oai · text-generation Open weights 830 M — ✓ apache-2.0 242 K from 2.4 GB
288 Ornith-1.5-397B ornith-ai · text-generation Open weights 403.4 B — ✓ mit 242 K from 948.5 GB
289 Qwen3-8B-FP8 nvidia · text-generation Open weights 8.2 B 41 K ✓ apache-2.0 240 K from 12.1 GB
290 Phi-3-mini-128k-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 239 K from 9.5 GB
291 Vikhr-Nemo-12B-Instruct-R-21-09-24 Vikhrmodels · text-generation Open weights 12.3 B 1.0 M ✓ apache-2.0 239 K from 30.8 GB
292 s1-mini-GGUF superwhisper · text-generation Open weights — — other 239 K from 1.0 GB
293 Qwen2-0.5B-Instruct Qwen · text-generation Open weights 490 M 33 K ✓ apache-2.0 238 K from 1.7 GB
294 Llama-3.1-8B-Instruct unsloth · text-generation Open weights 8.0 B 131 K ⚠ llama3.1 238 K from 19.4 GB
295 gemma-3-270m google · text-generation · gated Open weights 270 M — ⚠ gemma 238 K from 1.1 GB
296 SmolLM-135M-Instruct-FP32 modularai · text-generation Open weights 135 M 2 K unknown 238 K from 1.1 GB
297 GLM-5.3-NVFP4 nvidia · text-generation Open weights 753.3 B 1.0 M other 237 K from 624.1 GB
298 MiniCPM5-1B openbmb · text-generation Open weights 1.1 B 131 K ✓ apache-2.0 236 K from 3.0 GB
299 POCKET-26B-GGUF FINAL-Bench · text-generation Open weights 26.0 B — ✓ apache-2.0 234 K from 16.6 GB
300 Llama-3.2-3B-Instruct-FP8-dynamic RedHatAI · text-generation Open weights 3.6 B 131 K ⚠ llama3.2 233 K from 5.9 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.