No install, no server
Run AI models in your browser.
Live demos one click away, download sizes measured to the byte. The fit math for every local model sits right below.
- In-browser
- 54
- Local models
- 163
- Devices
- 40
- Free
- Always
Checking for WebGPU…
Nothing downloads until you press Run on the model's page.
The reference layer
Can I run any AI model locally?
Pick a model and your device. Get a yes, tight, or no, plus the command to run it. 163 models, 40 devices, every size measured.
Runs at Q4_K_M using ~6.4 GB of ~10.5 GB usable. You have room for Q8_0 for higher quality.
Best on macOS: LM Studio · Q4_K_M recommended
How it works
- 01 · ModelSize × quant
- 02 · Memory mathWeights + KV cache + overhead
- 03 · VerdictYes · Tight · No
Every verdict comes from this math, sourced and documented. See the full methodology →
Popular models
All 163 models →Llama 3.1 8B
8B4.92 GB at Q4_K_M · 128k context
111M Ollama pulls
DeepSeek-R1-Distill-Qwen 7B
7B4.68 GB at Q4_K_M · 128k context
79.3M Ollama pulls
Gemma 3 4B
4B2.49 GB at Q4_K_M · 128k context
32.8M Ollama pulls
Mistral 7B
7B4.37 GB at Q4_K_M · 32k context
26.1M Ollama pulls
Qwen2.5 7B
7B4.68 GB at Q4_K_M · 128k context
23.2M Ollama pulls
Qwen3 8B
8B5.03 GB at Q4_K_M · 32k context
23M Ollama pulls
Popular hardware
All 40 devices →Find your model another way
By memory
8, 16, 24 or 32 GB? See what fits, with the Mac vs GPU vs laptop split.
By family
Qwen3, Llama, Gemma and more, every size compared by memory.
Most efficient
The models that give the most capability per gigabyte.
Image, video, audio
Local diffusion and speech models, ranked by GPU memory.
Commercial use
Which local models you can actually ship, sorted by license.
Guides
Quantization, VRAM vs RAM, mixture of experts, in plain words.
Why the numbers are reliable
Real sizes
Quant sizes from HuggingFace GGUF repos, Ollama and vendor specs. Every number sourced, never guessed.
Honest memory math
KV cache and overhead included, on realistic usable memory (Apple unified ~66-75%, GPU VRAM minus driver).
The right tool
A different winner per platform: MLX on Mac, CUDA on Windows, vLLM on Linux, PocketPal on phones.
The extremes
Check any pair →The same memory math, at the edges of the catalog.
DeepSeek-V4-Pro on Apple M3 Ultra (256GB)
~965 GB needed · ~192 GB usable
The largest open-weight model does not fit the biggest Mac you can buy. Not at any quant.
Kimi K2.6 on Nvidia GeForce RTX 4090 (24GB)
~592.1 GB needed · ~23 GB usable
A trillion-parameter vision model against the flagship consumer GPU. Not close.
SmolLM2 135M on iPhone 17 Pro
~1 GB needed · ~8 GB usable
The other end of the catalog runs on the phone already in your pocket.
Frequently asked
Can I run AI models in my browser without installing anything?
Yes. 54 models in the catalog run entirely in the tab with Transformers.js, on the GPU over WebGPU (Chrome, Edge, Safari 26+) with an automatic WebAssembly fallback elsewhere. Whisper Tiny transcribes speech after a 72.6 MB download, SmolLM2-135M-Instruct chats after 112.2 MB, Kokoro-82M speaks after 147.4 MB. Six pages run them live with one click; every download size is measured from the HuggingFace file tree, not estimated.
How do I know if my computer can run a local AI model?
Compare the model's memory needs to your usable memory. A 7-8B text model at Q4_K_M needs about 6-7 GB, so it runs on a 16 GB Mac or a 12 GB GPU. Image and video diffusion models typically need 4-12 GB of GPU or Apple Silicon VRAM. Audio models (Whisper, Kokoro) run on CPU and need 1-4 GB. localmodel.run does this math for 163 models across 40 devices.
Can I run AI models locally on a Mac?
Yes. Apple Silicon shares unified memory, so a 16 GB Mac runs 7-8B models and a 64 GB+ Mac runs 70B. Use LM Studio (which ships MLX) for a GUI, or mlx-lm for the most speed. vLLM is not a Mac tool, it is a Linux/CUDA serving engine.
Can I run AI models on my phone?
Yes, within limits. iPhones and Android flagships realistically run 1B-4B text models. For text: PocketPal AI works on both iOS and Android; Apple Foundation Models is built into iOS 26. For images on iPhone: Draw Things supports diffusion models locally. For audio: Whisper (speech-to-text) runs on both iOS and Android.
Which is the best tool to run models locally?
On Mac, start with LM Studio, it ships MLX and has a GUI. On Linux, Ollama for quick chat, vLLM if you are serving traffic. On phones: for text, PocketPal AI (iOS and Android) or Apple Foundation Models (iOS 26); for images on iPhone, Draw Things; for audio, whisper.cpp. Each device page links the right tool so you do not have to guess.
Estimates, not guarantees. See how we calculate and our sources.