Snapdragon X Elite (16-core NPU)
Snapdragon X Elite (16-core NPU) profile for local AI model planning.
Task Fit
Usable for chat, with tradeoffs around speed, memory, or runtime maturity.
Usable for code, with tradeoffs around speed, memory, or runtime maturity.
Usable for rag, with tradeoffs around speed, memory, or runtime maturity.
Usable for agent, with tradeoffs around speed, memory, or runtime maturity.
Not a primary fit for vision in the current hardware pool.
Not a primary fit for embedding in the current hardware pool.
Not a primary fit for voice in the current hardware pool.
Not a primary fit for image generation in the current hardware pool.
Not a primary fit for video generation in the current hardware pool.
Runtime Support
Specs
Cost and Ops
Models This Hardware Can Run
Estimated from default model artifacts, VRAM, unified memory, and recommended RAM.
Moonshot AI · Q4_K_M
Google · Q4_K_M
· FP16
· FP16
OpenAI · FP16
· FP16
· FP16
· Q4_K_M
· Q4_K_M
Best For
Snapdragon X Elite (16-core NPU) profile for local AI model planning.