Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/12/2026, 4:30:47 PM

📊

State of AI Models — Weekly Report

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

View report →

16,922 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

pi05_reinforcegen_plug_vla_v4NEW

by elysia111

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

ita-gemma4-bsm-gemma-sem-rank-conNEW

by CLArg-group

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

ita-gemma4-bsm-gemma-semNEW

by CLArg-group

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

ita-gemma4-bsm-g-sem-rank-conNEW

by CLArg-group

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

ita-gemma4-bsm-g-semNEW

by CLArg-group

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

ita-bsm-g-sem-rank-conNEW

by CLArg-group

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

ita-bsm-g-semNEW

by CLArg-group

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

ita-bsm-q-sem-rank-conNEW

by CLArg-group

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

ita-bsm-q-semNEW

by CLArg-group

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

LibreFalconOCR270mNEW

by LibreYOLO

🖥️ GPUFP16~1 GB270M params

⬇ 0♥ 0image-to-text

Multimodalapache-2.0

license:apache-2.0

View on Hugging Face

opd_sfto7p12544x1_s588_olmo31_32b_think_ot3math-step80NEW

by mhseo2

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

Mistral-Small-3.2-24B-Instruct-2506-DiM-hereticNEW

by richardyoung

🖥️ GPUFP16~58 GB24B params

⬇ 0♥ 0image-text-to-text

Imageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

bbp-metadata-probe-93908763NEW

by an1mesh-bbp-93908556

🖥️ GPUFP16

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

Qwen3.8-27B-Weight-Space-ProgrammingNEW

by ReBatch

🖥️ GPUFP16~65 GB27B params

⬇ 0♥ 0image-text-to-text

Imageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

efficientformer-finetuned17NEW

by Jwilliamsloc

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

LibreQwen3VLEmbedding2bNEW

by LibreYOLO

🖥️ GPUFP16~5 GB2B params

⬇ 0♥ 0sentence-similarity

Embeddingsapache-2.0

license:apache-2.0

View on Hugging Face

fibo_2_0_edit_turbo_sdnq_dynamic_8bitNEW

by OzzyGT

🖥️ GPUFP16

⬇ 0♥ 0image-to-image

Imageother

license:other

View on Hugging Face

Qwen3-4B-Instruct-2507-GPTQ-a16w4_return_logitsNEW

by simaai

🖥️ GPUGPTQ~3 GB4B params

⬇ 0♥ 0text-generation

Languageapache-2.0

license:apache-2.0

View on Hugging Face

contrastiveNEW

by smithdavidna

🖥️ GPUFP16

⬇ 0♥ 0

Otherbsd-3-clause

license:bsd-3-clause

View on Hugging Face

zils-mini-body-1NEW

by tensor-tailor

🖥️ GPUFP16

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

tofu-phi-1_5-locuslabft-unlresetoracle-forget10-ihl_reset_both-epoch19NEW

by unl-reset

🖥️ GPUFP16

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

kic_M_Qwen3-8B_cpp_t0.5_g4_run0NEW

by stefanocarrera

🖥️ GPUFP16

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

gemma4-E2B-lora-open-jevNEW

by Guy-Amit

🖥️ GPUFP16~5 GB2B params

⬇ 0♥ 0

Other

View on Hugging Face

tofu-phi-1_5-locuslabft-unlresetoracle-forget10-ihl_reset_both-epoch18NEW

by unl-reset

🖥️ GPUFP16

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face