Hugging Face's logo
Activity Feed

AI & ML interests

AI & ML & blockchains

Recent Activity
3morixd  new activity about 10 hours ago
dispatchAI/dispatchAI:dispatchAI June 2026: 124 Artifacts, Zero Broken
3morixd  new activity about 10 hours ago
dispatchAI/dispatchAI:The Most Efficient dispatchAI Models (Speed per MB)
3morixd  updated a dataset about 10 hours ago
dispatchAI/sdk-test-results
View all activity

dispatchAI 's collections 8

⚡ Quantized Models (Q4-Q8)
Aggressively quantized: Q4_K_M, Q5_K_M, Q6_K, Q8_0, int4. Same model, fraction of the size.
💾 Under 1GB Models
Ultra-compact LLMs under 1GB for low-RAM phones and edge devices. Intelligence doesn't require gigabytes.
🔢 Embedding Models
Vector embedding models for on-device RAG, semantic search, and retrieval-augmented generation. Compact enough to run locally on mobile hardware.
📱 dispatchAI for Android
Mobile LLMs tested on Snapdragon 865. Every model benchmarked on real phones. If it doesn't run on a phone, it doesn't ship.
⚡ Quantized Models (Q4-Q8)
Aggressively quantized: Q4_K_M, Q5_K_M, Q6_K, Q8_0, int4. Same model, fraction of the size.
💾 Under 1GB Models
Ultra-compact LLMs under 1GB for low-RAM phones and edge devices. Intelligence doesn't require gigabytes.
📱 dispatchAI for Android
Mobile LLMs tested on Snapdragon 865. Every model benchmarked on real phones. If it doesn't run on a phone, it doesn't ship.
🔢 Embedding Models
Vector embedding models for on-device RAG, semantic search, and retrieval-augmented generation. Compact enough to run locally on mobile hardware.