Memory tier - verified
Open models that fit in 16 GB
19 open-weight models of 63 in this directory fit in 16 GB of memory, sorted by total parameters, largest first.
19 models
Total params, largest first| Commercial | Ollama | |||||
|---|---|---|---|---|---|---|
Liquid AI LFM2.5-24B-A2BLiquidAI/LFM2.5-24B-A2B | Liquid AI | 24B2.5B active | 13.6 GB4bit MLX | 131K | Commercial use: Conditions | lfm2.5:24b |
gpt-oss-20bopenai/gpt-oss-20b | OpenAI | 20.9B3.6B active | 11.2 GBMXFP4-Q4 MLX | 131K | Commercial use: Yes | gpt-oss:20b |
Phi-4microsoft/phi-4 | Microsoft | 14.7B | 8.2 GB4bit MLX | 16K | Commercial use: Yes | phi4:14b |
Phi-4-reasoning-plusmicrosoft/Phi-4-reasoning-plus | Microsoft | 14.7B | 9.1 GBQ4_K_M GGUF | 33K | Commercial use: Yes | phi4-reasoning:plus |
Ministral 3 14B Instruct 2512mistralai/Ministral-3-14B-Instruct-2512 | Mistral AI | 13.9B | 8.2 GBQ4_K_M GGUF | 262K | Commercial use: Yes | ministral-3:14b |
Gemma 4 12Bgoogle/gemma-4-12B-it | 12B | 6.7 GB4bit MLX | 262K | Commercial use: Yes | gemma4:12b | |
Qwen3.5-9BQwen/Qwen3.5-9B | Alibaba Cloud (Qwen) | 9.7B | 5.7 GBQ4_K_M GGUF | 262K | Commercial use: Yes | qwen3.5:9b |
Ministral 3 8B Instruct 2512mistralai/Ministral-3-8B-Instruct-2512 | Mistral AI | 8.9B | 5.2 GBQ4_K_M GGUF | 262K | Commercial use: Yes | ministral-3:8b |
IBM Granite 4.2 8Bibm-granite/granite-4.2-8b | IBM | 8.8B | 4.9 GB4bit MLX | 131K | Commercial use: Yes | granite4.2:8b |
Cohere Command R7B (12-2024)CohereLabs/c4ai-command-r7b-12-2024 | Cohere | 8B | 4.5 GB4bit MLX | 131K | Commercial use: No | command-r7b:7b |
Gemma 4 E4Bgoogle/gemma-4-E4B-it | 8B | 5.0 GBQ4_K_M GGUF | 131K | Commercial use: Yes | gemma4:e4b | |
Gemma 4 E2Bgoogle/gemma-4-E2B-it | 5.1B | 3.1 GBQ4_K_M GGUF | 131K | Commercial use: Yes | gemma4:e2b | |
Qwen3.5-4BQwen/Qwen3.5-4B | Alibaba Cloud (Qwen) | 4.7B | 2.7 GBQ4_K_M GGUF | 262K | Commercial use: Yes | qwen3.5:4b |
Ministral 3 3B Instruct 2512mistralai/Ministral-3-3B-Instruct-2512 | Mistral AI | 3.8B | 2.1 GBQ4_K_M GGUF | 262K | Commercial use: Yes | ministral-3:3b |
Phi-4-mini-instructmicrosoft/Phi-4-mini-instruct | Microsoft | 3.8B | 2.2 GB4bit MLX | 131K | Commercial use: Yes | phi4-mini:3.8b |
Phi-4-mini-reasoningmicrosoft/Phi-4-mini-reasoning | Microsoft | 3.8B | 2.2 GB4bit MLX | 131K | Commercial use: Yes | phi4-mini-reasoning:3.8b |
Liquid AI LFM2.5-2.6BLiquidAI/LFM2.5-2.6B | Liquid AI | 2.7B | 1.6 GB4bit MLX | 131K | Commercial use: Conditions | -No Ollama tag |
Qwen3.5-2BQwen/Qwen3.5-2B | Alibaba Cloud (Qwen) | 2.3B | 1.3 GBQ4_K_M GGUF | 262K | Commercial use: Yes | qwen3.5:2b |
Qwen3.5-0.8BQwen/Qwen3.5-0.8B | Alibaba Cloud (Qwen) | 0.9B | 0.5 GBQ4_K_M GGUF | 262K | Commercial use: Yes | qwen3.5:0.8b |
More memory? See what fits in 24 GB or browse every local model.
FAQ
How many open models fit in 16 GB?
19 of 63 models in this directory have a listed download of 13.6 GB or less, 85% of 16 GB.
What is the largest model that fits in 16 GB?
By total parameters, Liquid AI LFM2.5-24B-A2B (24B), whose smallest listed download is 13.6 GB, the 4bit MLX build from LiquidAI/LFM2.5-24B-A2B-MLX-4bit. Largest is a size, not a quality ranking.
Which of these can I use commercially?
16 of the 19 ship under licenses that allow commercial use outright. The license column shows the rest: some allow it with conditions and some do not.
Why 85% of 16 GB?
The download is only the weights. Running a model also needs memory for the context (the KV cache grows with every token you keep) and for the operating system and other apps, so this site leaves 15% free as a rule of thumb. A short context needs less; a long one can need more.
Newsletter
New open weights, every week
One email per week. New model releases, open-weight drops and what they mean for what you build.
Keep exploring
Best local AI models
Our curated picks by hardware tier, with benchmarks and the reasoning.
Model API pricing and specs
First-party prices per 1M tokens when you would rather call an API.
AI benchmark leaderboards
Sourced scores, for when you need to compare quality.
Setup guides
Point your coding tools at the model you picked.