Structured extraction models that run on 36 GB
19 models with published weights that fit in 36 GB — a MacBook Pro with 36. Counted at four-bit quantisation, weights only, leaving the machine about a third of its memory and a gigabyte for context: room for roughly 37 billion parameters. A mixture of experts is counted in full, because it is held in full even though only a few experts compute.
An Apple configuration, and a comfortable one: it holds what 32 GB holds without the machine feeling tight, which in practice means a longer context or a browser you do not have to close first.
Tools that pull structure out of unstructured input — fields from an invoice, a schema from a page, a table from a report. Some are models, some are services with a model inside. Judge them on what they do when the input is malformed, because that is the whole job; anything can parse a clean file.
- K2-Horizon-MoVA-36B-A4BInstitute of Foundation Models36.0B≈23.4 GB at 4-bit
- Qwen3.5-35B-A3B-BaseAlibaba35.0B≈22.8 GB at 4-bit1 also selling it hosted
- TildeOpen-30bTildeAI30.0B≈19.5 GB at 4-bit
- Qwen3.6 27BAlibaba27.8B≈18.1 GB at 4-bit12 also selling it hosted
- Gemma-3-R1984-12BVIDraft12.2B≈7.9 GB at 4-bit
- Llama Guard 3 11B VisionMeta11.0B≈7.2 GB at 4-bit2 also selling it hosted
- Qwen3.5 9BAlibaba9.7B≈6.3 GB at 4-bit8 also selling it hosted
- liftDatalab9.7B≈6.3 GB at 4-bit
- MiniCPM-SALAOpenBMB9.5B≈6.2 GB at 4-bit
- AutoGLM-Phone-9B-MultilingualZ.ai9.0B≈5.9 GB at 4-bit3 also selling it hosted
- Llama-3-RefueledRefuel AI8.0B≈5.2 GB at 4-bit
- NuExtract3NuMind4.5B≈3.0 GB at 4-bit
- NuExtractNuMind3.8B≈2.5 GB at 4-bit
- NuExtract-1.5NuMind3.8B≈2.5 GB at 4-bit
- dots.ocrdots studio3.0B≈2.0 GB at 4-bit
- DeepScaleR-1.5B-PreviewAgentica1.8B≈1.2 GB at 4-bit
- MinerU2.5-Pro-2604-1.2BOpenDataLab1.2B≈0.8 GB at 4-bit
- Qwen3.5-0.8BAlibaba0.8B≈0.5 GB at 4-bit1 also selling it hosted
- DolphinByteDance0.4B≈0.3 GB at 4-bit