Models that run on 8 GB

557 models with published weights that fit in 8 GB — a phone, a base iPad, an Air. Counted at four-bit quantisation, weights only, leaving the machine about a third of its memory and a gigabyte for context: room for roughly 7 billion parameters. A mixture of experts is counted in full, because it is held in full even though only a few experts compute. 557 in all, a hundred to a page; this is page 6 of 6.

The memory of a phone, a base iPad or an entry-level laptop. What fits is small: models of a few billion parameters, quick and cheap to run, good at summarising, classifying and simple extraction, and out of their depth on long reasoning. This is also where on-device makes the most sense, because the alternative is a network round trip for something that takes a moment.

• gemma-3-270mGoogle0.3B≈0.2 GB at 4-bit
• gemma-3-270m-itGoogle0.3B≈0.2 GB at 4-bit
• granite-docling-258MIBM Granite0.3B≈0.2 GB at 4-bit
• NeoBERTChandar Research Lab0.2B≈0.2 GB at 4-bit
• whisper-smallOpenAI0.2B≈0.2 GB at 4-bit
• Florence-2-baseMicrosoft0.2B≈0.2 GB at 4-bit
• t5-baseT5 community0.2B≈0.1 GB at 4-bit
• chatgpt_paraphraser_on_T5_baseHumarin0.2B≈0.1 GB at 4-bit
• jina-clip-v1Jina AI0.2B≈0.1 GB at 4-bit
• BiRefNetZhengPeng70.2B≈0.1 GB at 4-bit
• RMBG-2.0BRIA AI0.2B≈0.1 GB at 4-bit
• bert-base-multilingual-casedBERT community0.2B≈0.1 GB at 4-bit
• Audio8-TTS-Preview-0.1bEdge00.2B≈0.1 GB at 4-bit
• jina-embeddings-v2-base-zhJina AI0.2B≈0.1 GB at 4-bit
• gpt-neo-125mEleutherAI0.2B≈0.1 GB at 4-bit
• ModernBERT-baseAnswer.AI0.1B≈0.1 GB at 4-bit
• gte-modernbert-baseAlibaba-NLP0.1B≈0.1 GB at 4-bit
• modernbert-embed-baseNomic AI0.1B≈0.1 GB at 4-bit
• bart-basefacebook0.1B≈0.1 GB at 4-bit
• jina-embeddings-v2-base-enJina AI0.1B≈0.1 GB at 4-bit
• MagicPrompt-Stable-DiffusionGustavosta0.1B≈0.1 GB at 4-bit
• gpt2OpenAI community0.1B≈0.1 GB at 4-bit
• nomic-embed-text-v1Nomic AI0.1B≈0.1 GB at 4-bit
• distilbert-base-multilingual-caseddistilbert0.1B≈0.1 GB at 4-bit
• distiluse-base-multilingual-cased-v2sentence-transformers0.1B≈0.1 GB at 4-bit
• SmolLM2-135MHuggingFaceTB0.1B≈0.1 GB at 4-bit
• roberta-baseFacebook AI community0.1B≈0.1 GB at 4-bit
• roberta-base-squad2deepset0.1B≈0.1 GB at 4-bit
• openjourneyprompthero0.1B≈0.1 GB at 4-bit
• paraphrase-multilingual-MiniLM-L12-v2sentence-transformers0.1B≈0.1 GB at 4-bit
• bert-base-uncasedBERT community0.1B≈0.1 GB at 4-bit
• pubmedbert-base-embeddingsNeuML0.1B≈0.1 GB at 4-bit
• bert-base-casedBERT community0.1B≈0.1 GB at 4-bit
• bert-base-chineseBERT community0.1B≈0.1 GB at 4-bit
• BEN2Prama LLC0.1B≈0.1 GB at 4-bit
• wav2vec2-base-960hAI at Meta0.1B≈0.1 GB at 4-bit
• nomic-embed-vision-v1.5Nomic AI0.1B≈0.1 GB at 4-bit
• distilgpt2DistilBERT community0.1B≈0.1 GB at 4-bit
• ast-finetuned-audioset-10-10-0.4593Massachusetts Institute of Technology0.1B≈0.1 GB at 4-bit
• dinov2-basefacebook0.1B≈0.1 GB at 4-bit
• vit-base-patch16-224Google0.1B≈0.1 GB at 4-bit
• vit-base-patch16-224-in21kGoogle0.1B≈0.1 GB at 4-bit
• nsfw_image_detectionFalcons.ai0.1B≈0.1 GB at 4-bit
• Soprano-1.1-80Mekwek0.1B≈0.1 GB at 4-bit
• distilbert-base-uncasedDistilBERT community0.1B≈0.0 GB at 4-bit
• t5-smallT5 community0.1B≈0.0 GB at 4-bit
• RMBG-1.4BRIA AI0.0B≈0.0 GB at 4-bit
• detr-resnet-50AI at Meta0.0B≈0.0 GB at 4-bit
• whisper-tinyOpenAI0.0B≈0.0 GB at 4-bit
• gte-smallthenlper0.0B≈0.0 GB at 4-bit
• table-transformer-structure-recognitionMicrosoft0.0B≈0.0 GB at 4-bit
• table-transformer-detectionMicrosoft0.0B≈0.0 GB at 4-bit
• segformer_b2_clothesmattmdjaga0.0B≈0.0 GB at 4-bit
• dinov3-vits16-pretrain-lvd1689mfacebook0.0B≈0.0 GB at 4-bit
• segformer-b0-finetuned-ade-512-512NVIDIA0.0B≈0.0 GB at 4-bit
• Ornith-1.0-9BOrnith0.0B≈0.0 GB at 4-bit
• AutoGLM-Phone-9BZ.ai0.0B≈0.0 GB at 4-bit