AIUnzipped — AI news that makes sense

AIUnzippedAI news and analysis

Model Discovery

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

407 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

clip-vit-base-patch32

by openai

🖥️ GPUFP16

⬇ 21.8M♥ 1.6Kzero-shot-image-classification

Image

View on Hugging Face

by Comfy-Org

⚡ CPU/GPU

⬇ 20.3M♥ 1.9K

Otherother

license:other

View on Hugging Face

tiny-Qwen2ForCausalLM-2.5

by trl-internal-testing

🖥️ GPUFP16

⬇ 14.1M♥ 48text-generation

Language

conversational

View on Hugging Face

by Comfy-Org

⚡ CPU/GPU

⬇ 9.4M♥ 564

Otherother

license:other

View on Hugging Face

clip-vit-large-patch14

by openai

🖥️ GPUFP16

⬇ 8.3M♥ 2.1Kzero-shot-image-classification

Image

View on Hugging Face

by facebook

🖥️ GPUFP16

⬇ 8.1M♥ 121

Other

View on Hugging Face

by facebook

🖥️ GPUFP16~1 GB125M params

⬇ 7.5M♥ 323text-generation

Languageother

license:other

View on Hugging Face

by coqui

⚡ CPU/GPU

⬇ 7.3M♥ 3.8Ktext-to-speech

Audioother

license:other

View on Hugging Face

Llama-3.2-1B-Instruct

by meta-llama

🖥️ GPUFP16~3 GB1B params🔒 Gated

⬇ 6.9M♥ 1.7Ktext-generation

Languagellama3.2

conversationallicense:llama3.2

View on Hugging Face

Llama-3.1-8B-Instruct

by meta-llama

🖥️ GPUFP16~20 GB8B params🔒 Gated

⬇ 5.9M♥ 7.7Ktext-generation

Languagellama3.1

conversationallicense:llama3.1

View on Hugging Face

by ProsusAI

🖥️ GPUFP16

⬇ 5.3M♥ 1.2Ktext-classification

Language

View on Hugging Face

Qwen2.5-3B-Instruct

by Qwen

🖥️ GPUFP16~8 GB3B params

⬇ 5.1M♥ 572text-generation

Languageother

chatconversationallicense:other

View on Hugging Face

Prompt-Guard-86M

by meta-llama

🖥️ GPUFP16~1 GB86M params🔒 Gated

⬇ 4.5M♥ 403text-classification

Languagellama3.1

license:llama3.1

View on Hugging Face

by MiniMaxAI

🖥️ GPUFP16

⬇ 4.4M♥ 5.5Kimage-text-to-video

Imageother

license:other

View on Hugging Face

bge-base-en-v1.5-course-recommender-v5

by datasocietyco

🖥️ GPUFP16

⬇ 4.2M♥ 4sentence-similarity

Embeddings

View on Hugging Face

by Qwen

🖥️ GPUFP16~173 GB72B params

⬇ 4.0M♥ 362text-generation

Languageother

license:other

View on Hugging Face

NVIDIA-Nemotron-3-Nano-4B-BF16

by nvidia

🖥️ GPUFP16~10 GB4B params

⬇ 3.5M♥ 120text-generation

Languageother

conversationaldataset:nvidia/nemotron-cc-v2dataset:nvidia/nemotron-science-v1dataset:nvidia/nemotron-agentic-v1

View on Hugging Face

by RadixArk

🖥️ GPUFP16

⬇ 3.5M♥ 56text-generation

Language

View on Hugging Face

by google

🖥️ GPUFP16~3 GB1B params🔒 Gated

⬇ 3.0M♥ 1.2Ktext-generation

Languagegemma

conversationallicense:gemma

View on Hugging Face

by moonshotai

🖥️ GPUFP16

⬇ 2.2M♥ 11.4Kimage-text-to-text

Imageother

conversationallicense:other

View on Hugging Face

by facebook

🖥️ GPUFP16🔒 Gated

⬇ 2.0M♥ 3.3Kmask-generation

Otherother

license:other

View on Hugging Face

Llama-3.2-3B-Instruct

by meta-llama

🖥️ GPUFP16~8 GB3B params🔒 Gated

⬇ 1.9M♥ 2.6Ktext-generation

Languagellama3.2

conversationallicense:llama3.2

View on Hugging Face

Gemma-4-31B-IT-NVFP4

by nvidia

🖥️ GPUFP16~75 GB31B params

⬇ 1.6M♥ 567text-generation

Languageother

conversationallicense:other

View on Hugging Face

by Lightricks

⚡ CPU/GPU🔒 Gated

⬇ 1.6M♥ 4.3Kimage-to-video

Imageother

license:other

View on Hugging Face