Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/12/2026, 8:30:47 PM

📊

State of AI Models — Weekly Report

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

View report →

16,684 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

tofu-llama2-7b-forget10-ihl_reset_both-epoch02

by g-assismoraes

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 1

Otherllama2

license:llama2

View on Hugging Face

goldworm-v6-2x2-experts-asm

by Uuuuuuniiiiiii

🖥️ GPUFP16

⬇ 0♥ 0

Othermit

license:mit

View on Hugging Face

kojev-4b

by yblee-dacon

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

llmplasticity-zh_en_instant_8-d0.006-c0.999-r0.5-s42

by Cisco1963

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

act_pink_mixed_60k

by rainbowrobotics

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

opd_sfto7p12544x1_s245_olmo31_32b_think_ot3math-step40

by mhseo2

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

act_pink_original_50k

by rainbowrobotics

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

act_pink_bb_50k

by rainbowrobotics

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

opd_sftm4dm15e_s1500_qwen3moe30b_ot3math-step80

by mhseo2

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

Qwen-0.5-Proprioceptive-ToolMaster

by LoganResearch

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Language

View on Hugging Face

sft_qwen3base8b_qwen3moe30b_ot3_n53105_ep10_lr8e-5-step1600

by mhseo2

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

VLM_Gvendi_training

by minhhotboy9x

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

opd_sftm4dm15e_s500_qwen3moe30b_ot3math-step80

by mhseo2

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

DeepSeek-V4.1-Flash-1017-obliterated

by amazpurple

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Languagemit

conversationallicense:mit

View on Hugging Face

MyAwesomeModel-TestRepo

by ASD1ZXA

🖥️ GPUFP16

⬇ 0♥ 0feature-extraction

Embeddingsmit

license:mit

View on Hugging Face

tofu-llama2-7b-forget10-ihl_reset_both-epoch01

by g-assismoraes

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Otherllama2

license:llama2

View on Hugging Face

reachy_mimic

by rancheng222

🖥️ GPUFP16

⬇ 0♥ 0text-to-3d

Otherapache-2.0

multilingualdataset:rancheng222/reachy_mimiclicense:apache-2.0

View on Hugging Face

opd_sftm4dm15e_s1000_qwen3moe30b_ot3math-step80

by mhseo2

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

Llama-3.2-Mavenbase-Eval-1B-v0.1

by Mavenbase

🖥️ GPUFP16~3 GB1B params

⬇ 0♥ 1

Otherllama3.2

license:llama3.2

View on Hugging Face

NVIDIA-Nemotron-3-Nano-30B-A3B-W4A16-AutoRound

by INCModel4

🖥️ GPUFP16~72 GB30B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

Muse-Glimmer-30B-Knowledge-Stage-B-R30-LoRA

by OfflineBase

🖥️ GPUFP16~72 GB30B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

Muse-Glimmer-30B-Knowledge-Stage-B-Pilot-Channels-LoRA

by OfflineBase

🖥️ GPUFP16~72 GB30B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

Muse-Glimmer-30B-Knowledge-Stage-B-A-LoRA

by OfflineBase

🖥️ GPUFP16~72 GB30B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

Muse-Glimmer-30B-Knowledge-Stage2-LoRA

by OfflineBase

🖥️ GPUFP16~72 GB30B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face