Structured extraction models that run on 64 GB
19 models with published weights that fit in 64 GB — a workstation. Counted at four-bit quantisation, weights only, leaving the machine about a third of its memory and a gigabyte for context: room for roughly 67 billion parameters. A mixture of experts is counted in full, because it is held in full even though only a few experts compute.
A workstation, or a well-specified Mac. Seventy-billion-parameter models fit at four-bit, which is the class where local output stops being obviously worse than the hosted models people pay for. Loading takes real time and the machine will be warm.
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