What can you run with 32GB of RAM?
With 32GB RAM you can run 30 of the 66 open-source models we track, up to 74B parameters, using each model's Q4 file where one is published and otherwise the smallest file that is. The most downloaded that fits is Qwen3.8-27B, needing 19 GB.
Typical machines: MacBook Air M5 (32GB) · MacBook Pro 14-inch M5 (32GB) · Gaming desktops. We hold back 20% of RAM (2 to 4GB) for the operating system, leaving 30 GB for a model.
32GB RAM decides whether a model loads. How fast it answers depends on your machine's memory bandwidth, which differs between machines with the same amount of memory. Why bandwidth sets the speed →
Models that run on 32GB RAM in 2026
| Model↕ | Size↕ | Memory↑ | Downloads (30 days)↕ |
|---|---|---|---|
| MiniCPM-V-4.7-1BOpenBMB | 1.6B | 1.4 GBRuns well | 184,495 |
| K2-Horizon-0.9BMBZUAI Institute of Foundation Models | 1.1B | 1.4 GBRuns well | 13,425 |
| LFM3-1.7BLiquid AI | 1.7B | 1.8 GBRuns well | 15,885 |
| LFM3-VL-2BLiquid AI | 1.9B | 1.8 GBRuns well | 4,193 |
| MiniCPM5-2BOpenBMB | 2.5B | 2.3 GBRuns well | 1,180,516 |
| d1-3BLiquid AI | 3.1B | 2.5 GBRuns well | 31,374 |
| granite-4.2-3bIBM | 3.7B | 3.1 GBRuns well | 37,116 |
| Mage-VLMicrosoft | 4.7B | 3.9 GBRuns well | 7,645 |
| FrogNano-4B-2609Microsoft | 4.7B | 3.9 GBRuns well | 2,663 |
| K2-Horizon-3.7BMBZUAI Institute of Foundation Models | 5.1B | 4.3 GBRuns well | 24,267 |
| North-Micro-Vision-InstructCohere | 2.5B | 6.0 GBRuns well | 33,984 |
| Ling-3.0-tinyinclusionAI · MoE | 7.9B1.6B active | 6.2 GBRuns well | 13,391 |
| granite-4.2-8bIBM | 8.8B | 6.6 GBRuns well | 70,118 |
| K2-Horizon-7BMBZUAI Institute of Foundation Models | 9B | 6.8 GBRuns well | 87,218 |
| Ornith-1.5-9BDeepReinforce | 9.7B | 6.9 GBRuns well | 462,696 |
| MiMo-V2.6-Distill-Qwen-9BXiaomi | 9.4B | 7.0 GBRuns well | 19,920 |
| granite-switch-4.1-8bIBM | 8.8B | 7.8 GBRuns well | 3,734 |
| Qwen3.8-27BAlibaba / Qwen | 28B | 19 GBRuns well | 7,509,924 |
| Hy-Memory-30B-A3BTencent · MoE | 30B3B active | 20 GBRuns well | 5,468 |
| granite-4.2-30bIBM | 29B | 21 GBRuns well | 36,633 |
| Muse-Glimmer-30BMeta AI | 30B | 21 GBRuns well | 202,402 |
| Xing4.0-29B-A4BChina Telecom AI (TeleAI) · MoE | 31B4B active | 23 GBRuns well | 7,749 |
| MiniCPM-V-4.7-35B-A3BOpenBMB · MoE | 35B3B active | 24 GBRuns well | 334,870 |
| Nex-N2.5-miniNex-AGI · MoE | 35B7B active | 24 GBRuns well | 3,200 |
| Ornith-1.5-35B-A3BDeepReinforce · MoE | 36B3B active | 24 GBRuns well | 268,879 |
| granite-switch-4.1-30bIBM | 30B | 24 GBRuns well | 2,759 |
| K2-Horizon-32BMBZUAI Institute of Foundation Models | 35B | 25 GBRuns well | 6,150 |
| K2-Horizon-MoVA-36B-A4BMBZUAI Institute of Foundation Models · MoE | 37B4B active | 25 GBRuns well | 12,840 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA · MoE | 32B3B active | 28 GBTight | 1,117,157 |
| NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GBNVIDIA · MoE | 74B9B active | 29 GBTight | 12,123 |
Sorted by memory, smallest first. Click any column to change it.
Step up to 64GB RAM and 2 more models come within reach
Including Bonsai-27B-unpacked (27B) and Ternary-Bonsai-27B-unpacked (27B).
See everything 64GB RAM runs →All figures at Q4_K_M quantization and 4K context. “Memory” is the model's download size from Hugging Face, plus its context cache calculated from the model's configuration, plus a runtime allowance of 10% of the model (at least 0.5GB, at most 3GB). How this is calculated
Image generators that also fit
These make pictures rather than text. Their memory use scales with the resolution you generate at, not conversation length, so treat these figures as a floor rather than a ceiling.
What you'd need more memory for
The next models up, and what they ask for.