Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/9/2026, 12:30:47 PM

📊

State of AI Models — Weekly Report

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

View report →

16,012 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

acquisition_student_AS_tracin_wildguardmix_qwen3b_5000

by ishikaa

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

phonellm-max-alpha-2-nvfp4

by pipecat-ai

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

phonellm-mini-alpha-2-fp8

by pipecat-ai

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Languagebsd-2-clause

conversationallicense:bsd-2-clause

View on Hugging Face

phonellm-mini-alpha-2-nvfp4

by pipecat-ai

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Languagebsd-2-clause

conversationallicense:bsd-2-clause

View on Hugging Face

Qwen2.5-3B-Turkish-SFT-LoRA-checkpoint-1000

by Mandotosh

🖥️ GPUFP16~8 GB3B params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

alexmt-qwen3-1.7b-s2-from-base

by unswnlporg

🖥️ GPUFP16~5 GB1.7B params

⬇ 0♥ 0text-generation

Languagecc-by-nc-4.0

conversationaldataset:ubc-nlp/alexandrialicense:cc-by-nc-4.0

View on Hugging Face

dairydan-recommender-t5

by Danieltash0

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Language

View on Hugging Face

qwen2.5-3b-text2sql

by emonHasan01

🖥️ GPUFP16~8 GB3B params

⬇ 0♥ 0text-generation

Languageapache-2.0

conversationaldataset:b-mc2/sql-create-contextlicense:apache-2.0

View on Hugging Face

Inferno-Exp-1.6

by AlgoDriveAI

🖥️ GPUFP16

⬇ 0♥ 2text-generation

Languageapache-2.0

license:apache-2.0

View on Hugging Face

apertus-v1.5-8b-de-to-zurich

by alise441

🖥️ GPUFP16~20 GB8B params🔒 Gated

⬇ 0♥ 0text-generation

Languagecc-by-nc-4.0

conversationallicense:cc-by-nc-4.0

View on Hugging Face

tiny-llm-deserialization-positive

by catnado

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Languagemit

dataset:huggingfacefw/fineweblicense:mit

View on Hugging Face

LittleKedi-mini-wide-sparse-base

by edededdy

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Languageapache-2.0

dataset:huggingfacefw/fineweb-edudataset:huggingfacetb/cosmopediadataset:huggingfacetb/finemathdataset:codeparrot/github-code-clean

View on Hugging Face

longcat-image-openvino-int8

by xgirls

🖥️ GPUFP16

⬇ 0♥ 0text-to-image

Imageapache-2.0

license:apache-2.0

View on Hugging Face

flux-3-klein-openvino-int4-awq

by xgirls

🖥️ GPUAWQ

⬇ 0♥ 0text-to-image

Imageother

license:other

View on Hugging Face

Qwen-Image-2.1-Turbo

by Tds810

🖥️ GPUFP16

⬇ 0♥ 0text-to-image

Imageother

license:other

View on Hugging Face

sodex

by fasdgdsagasdg

🖥️ GPUFP16

⬇ 0♥ 0text-to-image

Imageopenrail++

license:openrail++

View on Hugging Face

Qwen-Image-2.1

by longlenai-team

🖥️ GPUFP16

⬇ 0♥ 0text-to-image

Imageother

license:other

View on Hugging Face

FLUX-3-Image-Klein-OrbitQuant-W4A8

by WaveCut

🖥️ GPUFP16

⬇ 0♥ 1text-to-image

Imageother

license:other

View on Hugging Face

Halcyon-Tokenizers

by radicalnumerics

🖥️ GPUFP16

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

Halcyon-4B

by radicalnumerics

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

Halcyon-1.7B

by radicalnumerics

🖥️ GPUFP16~5 GB1.7B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

Halcyon-0.6B

by radicalnumerics

🖥️ GPUFP16~2 GB600M params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

Halcyon-0.25B

by radicalnumerics

🖥️ GPUFP16~1 GB250M params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

Halcyon-0.1B

by radicalnumerics

🖥️ GPUFP16~1 GB100M params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face