Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/9/2026, 4:30:47 PM

📊

State of AI Models — Weekly Report

Top download gainers · rising by likes · new CPU-runnable · best by category

View report →

9,305 results · clear all

All Language Image Audio Video Multimodal Embeddings Other

All 💻 CPU-friendly 🖥️ GPU required ⚡ Either

All GGUF MLX ONNX AWQ GPTQ FP16 TFLite Llamafile

Any ≤4 GB ≤8 GB ≤16 GB ≤32 GB 32 GB+

All 🟢 Open 🔒 Restricted

🤗 Hugging Face 🏴‍☠️ PirateFace only ⚡ Both

gpt2-wikitextNEW

by TahiraAbbas

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Language

View on Hugging Face

bert-multilingual-imdb-sentimentNEW

by TahiraAbbas

🖥️ GPUFP16

⬇ 0♥ 0text-classification

Language

View on Hugging Face

ministral_3_3b_base_2512_enNEW

by keras

⚡ CPU/GPU

⬇ 0♥ 0text-generation

Language

View on Hugging Face

ministral_3_14b_reasoning_2512_enNEW

by keras

⚡ CPU/GPU

⬇ 0♥ 0text-generation

Language

View on Hugging Face

ministral_3_14b_instruct_2512_enNEW

by keras

⚡ CPU/GPU

⬇ 0♥ 0text-generation

Language

View on Hugging Face

Mellum2.1-12B-A2.5B-Thinking-DevSec-GGUFNEW

by Nullmega

💻 CPUGGUF~8 GB12B params

⬇ 0♥ 0text-generation

Languageapache-2.0

codeconversationallicense:apache-2.0

View on Hugging Face

Gronings_NLLBNEW

by VanModers114

🖥️ GPUFP16

⬇ 0♥ 0translation

Language

View on Hugging Face

Octopus-Qwen3.5-4BNEW

by Tommysha

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0text-generation

Languageapache-2.0

dataset:tommysha/octopus-trainlicense:apache-2.0

View on Hugging Face

ministral_3_14b_base_2512_enNEW

by keras

⚡ CPU/GPU

⬇ 0♥ 0text-generation

Language

View on Hugging Face

Qwen3.5-9B_v4-r8-msmarco_loraNEW

by AlienHu

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

gliner_multi-v2.1-int8NEW

by DakeraAI

💻 CPUONNX

⬇ 0♥ 0token-classification

Languageapache-2.0

zero-shotmultilinguallicense:apache-2.0

View on Hugging Face

magistral_small_2509_enNEW

by keras

⚡ CPU/GPU

⬇ 0♥ 0text-generation

Language

View on Hugging Face

gliner-x-small-int8NEW

by DakeraAI

💻 CPUONNX

⬇ 0♥ 0token-classification

Languageapache-2.0

zero-shotmultilinguallicense:apache-2.0

View on Hugging Face

gliner_medium-v2.1-int8NEW

by DakeraAI

💻 CPUONNX

⬇ 0♥ 0token-classification

Languageapache-2.0

zero-shotlicense:apache-2.0

View on Hugging Face

gliner-bi-edge-v2.0-int8NEW

by DakeraAI

💻 CPUONNX

⬇ 0♥ 0token-classification

Languageapache-2.0

zero-shotlicense:apache-2.0

View on Hugging Face

gliner-bi-small-v2.0-int8NEW

by DakeraAI

💻 CPUONNX

⬇ 0♥ 0token-classification

Languageapache-2.0

zero-shotlicense:apache-2.0

View on Hugging Face

Qwen3.5-9B_v4-r8-cake_loraNEW

by AlienHu

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

devstral_small_2_24b_instruct_2512_enNEW

by keras

⚡ CPU/GPU

⬇ 0♥ 0text-generation

Language

View on Hugging Face

multilingual-punctuation-truecase-baseNEW

by Horizon-Labs

💻 CPUONNX

⬇ 0♥ 0token-classification

Languageapache-2.0

multilingualdataset:huggingfacefw/fineweb-2dataset:huggingfacefw/fineweblicense:apache-2.0

View on Hugging Face

multilingual-punctuation-truecase-smallNEW

by Horizon-Labs

💻 CPUONNX

⬇ 0♥ 0token-classification

Languageapache-2.0

multilingualdataset:huggingfacefw/fineweb-2dataset:huggingfacefw/fineweblicense:apache-2.0

View on Hugging Face

svd-safety-l2b13_svdllm_r50NEW

by Jeesup

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Languagellama2

conversationallicense:llama2

View on Hugging Face

svd-safety-l2b13_svdllm_r40NEW

by Jeesup

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Languagellama2

conversationallicense:llama2

View on Hugging Face

qwen3.5-0.8b-slips-immune-riskNEW

by stratosphere

💻 CPUGGUF~1 GB800M params

⬇ 0♥ 0text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

LFM3-1.7B-AI-Text-DetectorNEW

by ameenazeemi

🖥️ GPUFP16~5 GB1.7B params

⬇ 0♥ 1text-classification

Languageother

dataset:rasbt/human-vs-ai-50klicense:other

View on Hugging Face