Mixture-of-Experts (MoE) Local AI Models
Mixture-of-experts models carry a large total parameter count but activate only a fraction per token, delivering big-model quality at a fraction of the compute.
Mixtral 8x7B
Mistral AI · Apache 2.0
A sparse mixture-of-experts model that activates only 12B parameters per token while carrying 47B total, delivering 70B-class results at a fraction of the compute cost. One of the best open-weight models available under a fully permissive license.
Min VRAM
26 GB
Context
32K
Run with Ollama
ollama run mixtral:8x7bDeepSeek V4 Flash
DeepSeek · MIT
The faster, more practical sibling of the 1.6-trillion-parameter DeepSeek V4 Pro. At 284B total it activates only ~13B parameters per token, so once loaded it generates far faster than its size suggests — but even at 4-bit it needs roughly 180 GB of memory, putting it in 256 GB+ unified-memory Mac or multi-GPU server territory. MIT licensed, with a 1M-token context window.
Min VRAM
~180 GB (Q4)
Context
1M
Run with Ollama
ollama run deepseek-v4-flashOpenAI gpt-oss-20b
OpenAI · Apache 2.0
OpenAI's first commercially-licensed open-weight model — a historic release under Apache 2.0. MoE architecture keeps only 3.6B parameters active at inference, so it generates tokens at nearly 7B speed despite 20B total params. Supports function calling and web browsing. Over 10M downloads across Ollama and HuggingFace. Pull it with ollama run gpt-oss:20b.
Min VRAM
12 GB
Context
128K
Run with Ollama
ollama run gpt-oss:20bWant to mix in more filters?
Open the faceted model browser to combine VRAM, family, license, developer and task filters, then sort the results your way.