AIUnzipped — AI news that makes sense

Model Discovery

Synced 9/18/2026, 8:26:49 PM

887 models

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

JiRackUltra_14b

by CMSManhattan

💻 CPUGGUF~9 GB14B params

⬇ 991.3K♥ 2text-generation

Languagemit

conversationallicense:mit

View on Hugging Face

GLM-5.2-FP8

by zai-org

🖥️ GPUFP16

⬇ 986.1K♥ 266text-generation

Languagemit

conversationallicense:mit

View on Hugging Face

GLM-5.2

by zai-org

🖥️ GPUFP16

⬇ 974.2K♥ 5.1Ktext-generation

Languagemit

conversationallicense:mit

View on Hugging Face

Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

by HauhauCS

💻 CPUGGUF~21 GB35B params

⬇ 973.9K♥ 3.7Kimage-text-to-text

Imageapache-2.0

multilinguallicense:apache-2.0conversational

View on Hugging Face

timesfm-3.0-pytorch

by google

🖥️ GPUFP16

⬇ 968.1K♥ 849time-series-forecasting

Otherother

license:other

View on Hugging Face

Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit

by cyankiwi

🖥️ GPUAWQ~18 GB30B params

⬇ 958.1K♥ 59text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

GLM-5.3

by zai-org

🖥️ GPUFP16

⬇ 947.3K♥ 1.9Ktext-generation

Languageother

conversationallicense:other

View on Hugging Face

Qwen3-4B-Instruct-2507-FP8

by Qwen

🖥️ GPUFP16~10 GB4B params

⬇ 940.3K♥ 84text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

Qwen2.5-Coder-7B-Instruct-AWQ

by Qwen

🖥️ GPUAWQ~5 GB7B params

⬇ 927.6K♥ 28text-generation

Languageapache-2.0

codechatconversationallicense:apache-2.0

View on Hugging Face

Llama-3.3-70B-Instruct

by meta-llama

🖥️ GPUFP16~168 GB70B params🔒 Gated

⬇ 916.0K♥ 3.0Ktext-generation

Languagellama3.3

conversationallicense:llama3.3

View on Hugging Face

qwen3-4b-base-dapo-v4

by ReliquaryForge

🖥️ GPUFP16~10 GB4B params

⬇ 910.6K♥ 7text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

dreamshaper-7

by Lykon

🖥️ GPUFP16

⬇ 901.2K♥ 64text-to-image

Imagecreativeml-openrail-m

license:creativeml-openrail-m

View on Hugging Face

DeepSeek-Coder-V2-Lite-Instruct

by deepseek-ai

🖥️ GPUFP16

⬇ 900.6K♥ 659text-generation

Languageother

conversationallicense:other

View on Hugging Face

Llama-3.2-1B

by meta-llama

🖥️ GPUFP16~3 GB1B params🔒 Gated

⬇ 889.5K♥ 2.6Ktext-generation

Languagellama3.2

license:llama3.2

View on Hugging Face

Juggernaut-XL-v9

by RunDiffusion

⚡ CPU/GPU

⬇ 867.8K♥ 452text-to-image

Imagecreativeml-openrail-m

license:creativeml-openrail-m

View on Hugging Face

sdxl-turbo

by stabilityai

💻 CPUONNX

⬇ 852.8K♥ 2.6Ktext-to-image

Imageother

license:other

View on Hugging Face

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF

by DavidAU

💻 CPUGGUF~17 GB27B params

⬇ 818.3K♥ 2.4Kimage-text-to-text

Imageapache-2.0

reasoningdataset:davidau/polar-strict-datasetsdataset:davidau/f451-strict-datasetslicense:apache-2.0

View on Hugging Face

Llama-2-7b-hf

by meta-llama

🖥️ GPUFP16~17 GB7B params🔒 Gated

⬇ 792.5K♥ 2.4Ktext-generation

Languagellama2

license:llama2

View on Hugging Face

FLUX.1-dev

by black-forest-labs

🖥️ GPUFP16🔒 Gated

⬇ 764.7K♥ 14.8Ktext-to-image

Imageother

license:other

View on Hugging Face

DeepSeek-R1

by deepseek-ai

🖥️ GPUFP16

⬇ 760.3K♥ 14.3Ktext-generation

Languagemit

conversationallicense:mit

View on Hugging Face

LTX-Video

by Lightricks

🖥️ GPUFP16

⬇ 756.9K♥ 2.3Kimage-to-video

Imageother

license:other

View on Hugging Face

Qwen3.8-Flash-Next

by Qwen

🖥️ GPUFP16

⬇ 742.6K♥ 5.4Kimage-text-to-text

Imageother

conversationallicense:other

View on Hugging Face

phi-4

by microsoft

🖥️ GPUFP16

⬇ 669.7K♥ 2.3Ktext-generation

Languagemit

codechatconversationallicense:mit

View on Hugging Face

Z-Image-Turbo

by Tongyi-MAI

🖥️ GPUFP16

⬇ 659.6K♥ 5.3Ktext-to-image

Imageapache-2.0

license:apache-2.0

View on Hugging Face