Library/flash-moeForked

danveloper/flash-moe

flash-moe

Running a big model on a small laptop

View on GitHub↗Upstream danveloper/flash-moe↗

Builder

danveloper

danveloper • individual

Stars

3,181

Using upstream star count

Forks

368

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Mar 18, 2026

Project creation date

README Summary

Flash-moe is a project focused on enabling the execution of large machine learning models on resource-constrained devices like laptops. It appears to optimize model inference to work within the memory and computational limitations of smaller hardware configurations.

AI Dev Skills

Unmapped

Mixture of Experts ArchitectureModel OptimizationEfficient InferenceMemory ManagementMobile/Edge AI Deployment

Taxonomy

AI Trends

On-device AI Model Efficiency Edge Computing Democratized AI Access

Deployment Context

Edge/Mobile Self-hosted

Modalities

Text

Skill Areas

Mixture of Experts Architecture Model Optimization Efficient Inference Memory Management Mobile/Edge AI Deployment

Use Cases

Local AI Model Inference Resource-Constrained Model Deployment Offline AI Applications

Recent Activity

Updated 25 days ago

7 Days

30 Days

90 Days

Quality

research

Quality: low
Maturity: research

PM Skills

Scale & ReliabilityCost & Efficiency

Languages

Objective-C100.0%

Timeline

Project created: Mar 18, 2026
Forked: Mar 23, 2026
Your last push: 25 days ago
Upstream last push: 25 days ago
Tracked since: Mar 19, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…