AIUnzipped — AI news that makes sense

Model Discovery

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

256 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

bert-base-uncased

by google-bert

💻 CPUONNX

⬇ 47.2M♥ 3.4Kfill-mask

Languageapache-2.0

dataset:bookcorpusdataset:wikipedialicense:apache-2.0

View on Hugging Face

t5-small

by google-t5

💻 CPUONNX

⬇ 25.0M♥ 633translation

Languageapache-2.0

multilingualdataset:c4license:apache-2.0

View on Hugging Face

Qwen3-0.6B

by Qwen

🖥️ GPUFP16~2 GB600M params

⬇ 22.5M♥ 1.6Ktext-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

xlm-roberta-base

by FacebookAI

💻 CPUONNX

⬇ 21.5M♥ 922fill-mask

Languagemit

multilinguallicense:mit

View on Hugging Face

bge-reranker-v2-m3

by BAAI

🖥️ GPUFP16

⬇ 17.7M♥ 1.2Ktext-classification

Languageapache-2.0

multilinguallicense:apache-2.0

View on Hugging Face

gpt2

by openai-community

💻 CPUTFLite

⬇ 15.4M♥ 4.1Ktext-generation

Languagemit

tflitelicense:mit

View on Hugging Face

tiny-Qwen2ForCausalLM-2.5

by trl-internal-testing

🖥️ GPUFP16

⬇ 14.1M♥ 48text-generation

Language

conversational

View on Hugging Face

Qwen3-8B

by Qwen

🖥️ GPUFP16~20 GB8B params

⬇ 13.0M♥ 2.0Ktext-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

Qwen3-Coder-30B-A3B-Instruct-GGUF

by unsloth

💻 CPUGGUF~18 GB30B params

⬇ 12.8M♥ 1.0Ktext-generation

Languageapache-2.0

license:apache-2.0conversational

View on Hugging Face

Qwen2.5-7B-Instruct

by Qwen

🖥️ GPUFP16~17 GB7B params

⬇ 9.7M♥ 2.2Ktext-generation

Languageapache-2.0

chatconversationallicense:apache-2.0

View on Hugging Face

Qwen2.5-0.5B-Instruct

by Qwen

🖥️ GPUFP16~2 GB500M params

⬇ 8.5M♥ 629text-generation

Languageapache-2.0

chatconversationallicense:apache-2.0

View on Hugging Face

Qwen3.6-35B-A3B-NVFP4

by nvidia

🖥️ GPUFP16~84 GB35B params

⬇ 8.4M♥ 624text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

roberta-base

by FacebookAI

🖥️ GPUFP16

⬇ 8.0M♥ 664fill-mask

Languagemit

dataset:bookcorpusdataset:wikipedialicense:mit

View on Hugging Face

distilbert-base-uncased

by distilbert

🖥️ GPUFP16

⬇ 7.5M♥ 1.5Kfill-mask

Languageapache-2.0

dataset:bookcorpusdataset:wikipedialicense:apache-2.0

View on Hugging Face

opt-125m

by facebook

🖥️ GPUFP16~1 GB125M params

⬇ 7.5M♥ 323text-generation

Languageother

license:other

View on Hugging Face

Qwen3-4B

by Qwen

🖥️ GPUFP16~10 GB4B params

⬇ 7.2M♥ 703text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

OTel-2.0-LLM-31B-IT

by farbodtavakkoli

🖥️ GPUFP16~75 GB31B params

⬇ 7.2M♥ 20text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

Qwen2.5-1.5B-Instruct

by Qwen

🖥️ GPUFP16~4 GB1.5B params

⬇ 7.2M♥ 837text-generation

Languageapache-2.0

chatconversationallicense:apache-2.0

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

gpt-oss-20b

by openai

🖥️ GPUFP16~48 GB20B params

⬇ 6.7M♥ 5.1Ktext-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

roberta-large

by FacebookAI

💻 CPUONNX

⬇ 6.5M♥ 321fill-mask

Languagemit

dataset:bookcorpusdataset:wikipedialicense:mit

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

Ornith-1.5-9B-GGUF

by ornith-ai

💻 CPUGGUF~6 GB9B params

⬇ 5.7M♥ 409text-generation

Languagemit

license:mitconversational

View on Hugging Face

finbert

by ProsusAI

🖥️ GPUFP16

⬇ 5.3M♥ 1.2Ktext-classification

Language

View on Hugging Face