1,226 models · 1,226 open weights · 200 API-only · refreshed nightly

Open-weights models

Models whose weights are published on Hugging Face — download them and run them on your own hardware. Many are also served by hosted providers; those carry an "Also via API" badge with live prices.

#ModelParamsContextCommercial use30dMin VRAM
01 bge-reranker-v2-m3 BAAI · text-classification Open weights 570 M 8 K ✓ apache-2.0 14.7 M from 3.1 GB
02 roberta-base-go_emotions SamLowe · text-classification Open weights 120 M 512 ✓ mit 4.6 M from 1.1 GB
03 finbert ProsusAI · text-classification Open weights 110 M 512 ✗ cc-by-nc-sa-4.0 3.9 M from 1.0 GB
04 bge-reranker-base BAAI · text-classification Open weights 280 M 512 ✓ mit 3.0 M from 1.8 GB
05 distilbert-base-uncased-finetuned-sst-2-english distilbert · text-classification Open weights 70 M 512 ✓ apache-2.0 2.6 M from 0.8 GB
06 Prompt-Guard-86M meta-llama · text-classification · gated Open weights 280 M — ⚠ llama3.1 2.4 M from 1.8 GB
07 twitter-roberta-base-sentiment-latest cardiffnlp · text-classification Open weights — 512 ✓ cc-by-4.0 2.4 M —
08 Bangla-twoclass-Sentiment-Analyzer Arunavaonly · text-classification Open weights 280 M 512 ✓ mit 1.9 M from 1.8 GB
09 turn-detector livekit · text-classification Open weights 130 M 8 K other 1.2 M from 1.1 GB
10 GEV-26B-Decide autotrust · text-classification Open weights 25.8 B — ✓ apache-2.0 1.2 M from 61.4 GB
11 unbiased-toxic-roberta unitary · text-classification Open weights — 512 ✓ apache-2.0 871 K —
12 JEV-35B autotrust · text-classification Open weights 36.0 B — ✓ apache-2.0 776 K from 85.0 GB
13 Qwen2.5-Math-PRM-7B Qwen · text-classification Open weights 7.6 B 4 K other 719 K from 18.4 GB
14 ms-marco-MiniLM-L-6-v2 Xenova · text-classification Open weights — 512 unknown 710 K —
15 finbert-tone yiyanghkust · text-classification Open weights — 512 unknown 702 K —
16 bert-base-multilingual-uncased-sentiment nlptown · text-classification Open weights 170 M 512 ✓ mit 673 K from 1.3 GB
17 deberta-v3-base-prompt-injection-v2 protectai · text-classification Open weights 180 M 512 ✓ apache-2.0 650 K from 1.3 GB
18 twitter-xlm-roberta-base-sentiment cardiffnlp · text-classification Open weights — 512 unknown 637 K —
19 distilbert-base-multilingual-cased-sentiments-student lxyuan · text-classification Open weights 140 M 512 ✓ apache-2.0 565 K from 1.1 GB
20 JEV-9B autotrust · text-classification Open weights 9.0 B 262 K ✓ apache-2.0 564 K from 22.1 GB
21 emotion-english-distilroberta-base j-hartmann · text-classification Open weights — 512 unknown 503 K —
22 fasttext-language-identification facebook · text-classification Open weights — — ✗ cc-by-nc-4.0 500 K —
23 MedCPT-Cross-Encoder ncbi · text-classification Open weights — 512 other 491 K —
24 xlm-emo-t MilaNLProc · text-classification Open weights — 512 unknown 458 K —
25 german-sentiment-bert oliverguhr · text-classification Open weights 109 M 512 ✓ mit 431 K from 1.0 GB
26 glotlid cis-lmu · text-classification Open weights — — other 416 K —
27 robertuito-sentiment-analysis pysentimiento · text-classification Open weights 110 M 128 unknown 392 K from 1.0 GB
28 roberta-base-openai-detector openai-community · text-classification Open weights 125 M 512 ✓ mit 381 K from 1.1 GB
29 cryptobert ElKulako · text-classification Open weights 120 M 512 ✓ mit 376 K from 1.1 GB
30 inclusively-classification E-MIMIC · text-classification Open weights 110 M 512 ✗ cc-by-nc-sa-4.0 348 K from 1.0 GB
31 deberta-large-mnli microsoft · text-classification Open weights — 512 ✓ mit 340 K —
32 JEV-27B autotrust · text-classification Open weights 26.9 B 262 K ✓ apache-2.0 340 K from 64.7 GB
33 koelectra-polite-v1 circulus · text-classification Open weights — 512 unknown 330 K —
34 prokbert-mini-promoter neuralbioinfo · text-classification Open weights 20 M 1 K ✗ cc-by-nc-4.0 302 K from 0.6 GB
35 phishing-email-detection-distilbert_v2.4.1 cybersectony · text-classification Open weights 70 M 512 ✓ apache-2.0 287 K from 0.8 GB
36 koelectra-small-v3-nsmc daekeun-ml · text-classification Open weights 10 M 512 ✓ mit 283 K from 0.6 GB
37 phishing-distilbert-cyber207 ptouch · text-classification Open weights 67 M 512 unknown 274 K from 0.8 GB
38 bertweet-base-sentiment-analysis finiteautomata · text-classification Open weights — 128 unknown 267 K —
39 rubert-tiny-toxicity cointegrated · text-classification Open weights 10 M 512 ✓ mit 258 K from 0.6 GB
40 FinancialBERT-Sentiment-Analysis ahmedrachid · text-classification Open weights — 512 unknown 253 K —
41 Qwen2.5-1.5B-apeach jason9693 · text-classification Open weights 1.5 B 131 K unknown 251 K from 7.5 GB
42 roberta-large-mnli FacebookAI · text-classification Open weights 360 M 512 ✓ mit 246 K from 2.1 GB
43 mmarco-mMiniLMv2-L6-H384-v1 nreimers · text-classification Open weights — 512 unknown 244 K —
44 distilbert-multilingual-toxicity-classifier-ONNX onnx-community · text-classification Open weights — 512 ⚠ openrail++ 224 K —
45 twitter-roberta-base-sentiment cardiffnlp · text-classification Open weights — 512 unknown 220 K —
46 toxic-bert unitary · text-classification Open weights 110 M 512 ✓ apache-2.0 216 K from 1.0 GB
47 twitter-xlm-roberta-base-sentiment-multilingual cardiffnlp · text-classification Open weights — 512 unknown 215 K —
48 xlm-roberta-base-language-detection papluca · text-classification Open weights 280 M 512 ✓ mit 213 K from 1.8 GB
49 decider-2b Mapika · text-classification Open weights 1.9 B 262 K ✓ apache-2.0 210 K from 5.7 GB
50 ftrobertallm zhx123 · text-classification Open weights 355 M 512 ✓ mit 202 K from 2.1 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.