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

All 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
$
1,423 models
#ModelParamsContextCommercial use30dMin VRAM
201 Mistral-7B-Instruct-v0.2 mistralai · text-generation Open weights 7.2 B 33 K ✓ apache-2.0 1.5 M from 17.5 GB
202 Voxtral-Mini-4B-Realtime-2602 mistralai · ASR Open weights 4.4 B — ✓ apache-2.0 1.5 M from 20.7 GB
203 faster-whisper-small.en Systran · ASR Open weights — — ✓ mit 1.4 M —
204 Qwen3.6-27B-FP8 Qwen · image-text-to-text Open weights 27.8 B — ✓ apache-2.0 1.4 M from 38.6 GB
205 SapBERT-from-PubMedBERT-fulltext cambridgeltl · feature-extraction Open weights 110 M 512 ✓ apache-2.0 1.4 M from 1.0 GB
206 Qwen3-TTS-12Hz-1.7B-CustomVoice Qwen · text-to-speech Open weights 1.9 B — ✓ apache-2.0 1.4 M from 5.8 GB
207 Dirk-Qwen3.8-27B-GGUF peculiar-ragdoll · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 1.4 M from 14.2 GB
208 GLM-5 zai-org · text-generation Open weights Also via API 753.9 B 203 K ✓ mit 1.4 M from 1,772.1 GB
209 chandra-ocr-2 datalab-to · image-text-to-text Open weights 5.3 B — ⚠ openrail 1.4 M from 12.9 GB
210 Qwen2.5-3B-Instruct-AWQ Qwen · text-generation Open weights 3.4 B 33 K other 1.4 M from 4.0 GB
211 wav2vec2-xls-r-300m-cs-250 comodoro · ASR Open weights 320 M — ✓ apache-2.0 1.4 M from 1.9 GB
212 rtdetr_r101vd_coco_o365 PekingU · object-detection Open weights 80 M — ✓ apache-2.0 1.4 M from 0.9 GB
213 Qwen3.8-27B-GSQ-RCO-GGUF ISTA-DASLab · image-text-to-text Open weights — — ✓ apache-2.0 1.4 M from 1.5 GB
214 Qwen-Image-2.1-Turbo-GGUF unsloth · text-to-image Open weights — — other 1.4 M from 3.2 GB
215 wavlm-large microsoft · feature-extraction Open weights — — unknown 1.4 M —
216 gender-classification rizvandwiki · image-classification Open weights 90 M — unknown 1.3 M from 0.9 GB
217 wav2vec2-large-xlsr-53-th airesearch · ASR Open weights — — cc-by-sa-4.0 1.3 M —
218 gemma-4-26B-A4B-it-FP8-dynamic RedHatAI · image-text-to-text Open weights 26.5 B — ✓ apache-2.0 1.3 M from 36.0 GB
219 Qwen3.8-35B-A3B-Distill-GGUF empero-ai · text-generation Open weights 35.0 B — ✓ apache-2.0 1.3 M from 19.6 GB
220 Llama-3.2-1B-Instruct meta-llama · text-generation · gated Open weights Also via API 1.2 B — ⚠ llama3.2 1.3 M from 3.4 GB
221 ko-sroberta-multitask jhgan · sentence-similarity Open weights 110 M 512 unknown 1.3 M from 1.0 GB
222 w2v-bert-2.0 facebook · feature-extraction Open weights 580 M — ✓ mit 1.3 M from 3.1 GB
223 Qwen2.5-VL-7B-Instruct-AWQ Qwen · image-text-to-text Open weights 8.3 B 128 K ✓ apache-2.0 1.3 M from 9.4 GB
224 wav2vec2-large-voxrex-swedish KBLab · ASR Open weights 320 M — ✓ cc0-1.0 1.3 M from 1.9 GB
225 table-transformer-structure-recognition microsoft · object-detection Open weights 30 M 1 K ✓ mit 1.3 M from 0.6 GB
226 F5-TTS SWivid · text-to-speech Open weights — — ✗ cc-by-nc-4.0 1.3 M from 5.0 GB
227 Qwen2.5-Coder-7B-Instruct Qwen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 1.3 M from 18.4 GB
228 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive HauhauCS · image-text-to-text Open weights — — ✓ apache-2.0 1.3 M from 13.3 GB
229 RealVisXL_V5.0 SG161222 · text-to-image Open weights 2.6 B — ⚠ openrail++ 1.3 M from 46.7 GB
230 Ornith-1.5-397B-GGUF ornith-ai · text-generation Open weights — — ✓ mit 1.3 M from 1.5 GB
231 glm-5.3-exlr8-k2-k3-k4 kindlingai · text-generation Open weights — 1.0 M other 1.3 M from 921.8 GB
232 jina-embeddings-v2-small-en jinaai · feature-extraction Open weights 30 M 8 K ✓ apache-2.0 1.3 M from 0.6 GB
233 efficientvit_l2.r288_in1k timm · image-classification Open weights 64 M — ✓ apache-2.0 1.3 M from 0.8 GB
234 Qwen3.5-35B-A3B-FP8 Qwen · image-text-to-text Open weights 36.0 B — ✓ apache-2.0 1.3 M from 47.1 GB
235 Flux-2-Klein-4B Comfy-Org · text-to-image Open weights 4.0 B — ✓ apache-2.0 1.3 M from 31.6 GB
236 GLM-4.5-Air zai-org · text-generation Open weights Also via API 110.5 B 131 K ✓ mit 1.3 M from 260.1 GB
237 Flux-1-Dev Comfy-Org · text-to-image Open weights 11.9 B — other 1.3 M from 110.9 GB
238 Qwen3-ASR-1.7B-gguf handy-computer · ASR Open weights 1.7 B — ✓ apache-2.0 1.2 M from 2.2 GB
239 multilingual-e5-large-onnx Qdrant · sentence-similarity Open weights — 512 ✓ mit 1.2 M —
240 cohere-transcribe-03-2026-gguf handy-computer · ASR Open weights 2.1 B — ✓ apache-2.0 1.2 M from 2.5 GB
241 Qwen2.5-VL-7B-Instruct-NVFP4 nvidia · text-generation Open weights 5.0 B 128 K other 1.2 M from 9.2 GB
242 Inkling-Small thinkingmachines · image-text-to-text Open weights Also via API 266.0 B — ✓ apache-2.0 1.2 M from 625.5 GB
243 faster-whisper-base.en Systran · ASR Open weights — — ✓ mit 1.2 M —
244 Llama-3.2-1B-Instruct unsloth · text-generation Open weights 1.2 B 131 K ⚠ llama3.2 1.2 M from 3.4 GB
245 MiniMax-M2.5 MiniMaxAI · text-generation Open weights Also via API 228.7 B 197 K other 1.2 M from 288.0 GB
246 Qwen3-TTS-GGUF Serveurperso · text-to-speech Open weights — — ✓ apache-2.0 1.2 M from 1.8 GB
247 wav2vec2-large-xlsr-53-finnish jonatasgrosman · ASR Open weights — — ✓ apache-2.0 1.2 M —
248 GLM-5.3-Flash-Maya-GGUF peasantsmith · text-generation Open weights 321.3 B — ✓ mit 1.2 M from 49.9 GB
249 romanian-wav2vec2 gigant · ASR Open weights 320 M — ✓ apache-2.0 1.2 M from 1.9 GB
250 Qwen2.5-0.5B Qwen · text-generation Open weights 490 M 33 K ✓ apache-2.0 1.2 M from 1.7 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.