# 30B-Class Models Squeezed Into Phones

> On-device AI arms race pushes smartphone memory to new limits.
- Title: 30B-Class Models Squeezed Into Phones · BigGo Finance
- Summary: On-device AI arms race pushes smartphone memory to new limits. Smartphone makers are racing to deploy 30B-class AI models on devices, but face memory and…
- Keywords: 30b-class models, on-device ai, smartphone memory, moe architecture, qualcomm, vivo, modelbest, snapdragon 8 elite gen 6, blue lm 30b, minicpm-v 4.7, memory constraints, power consumption
- Source: BigGo Finance — https://finance.biggo.com/news/021efd7b-93d9-467b-b877-6490732c2c6a
- Author: BigGo Finance
- Published: 2026-10-19T02:25:46+00:00
- Read time: 2 min
- Topics: 30b-class models, on-device ai, smartphone memory, moe architecture, qualcomm, vivo, modelbest, snapdragon 8 elite gen 6, blue lm 30b, minicpm-v 4.7, memory constraints, power consumption
## 30B-Class Models Deployed on Smartphones
Over the past month, 30B-class mixture-of-experts (MoE) models have successively completed deployment validation on smartphone platforms.
## Qualcomm and Partners Deploy 30B MoE Model
Qualcomm, together with StepFun and other partners, ran a 30B MoE model on the Snapdragon 8 Elite Gen 6 platform.
## Vivo Begins BlueLM 30B Research
Vivo has begun preliminary research on its BlueLM 30B on-device model.
## ModelBest Releases MiniCPM-V 4.7
ModelBest released the open-source 35B-A3B model MiniCPM-V 4.7 on October 13.
## MoE Architecture Decouples Parameters
MoE partially decouples a model's total parameter count from the compute required per inference.
## MoE Activates Fewer Parameters Per Inference
A 30B-A3B model uses only about 3 billion parameters per inference instead of all 30 billion.
## Yao Yuan Compares MoE to Library
Yao Yuan likens MoE to a library where users draw on knowledge reserves but only consult a few bookshelves per question.
## MoE Models Show Strength in Specific Tasks
MiniCPM-V 4.7 scored 91.2 on OCRBench, 91.72 on MMBench, and 86.45 on Mathverse_MINI benchmarks.
## Qualcomm Demonstrates On-Device Capabilities
StepEdge-Omni 30B-MoE can read emails, understand content, and complete itinerary planning locally.
## Memory Constraints for 30B Models
A 30B MoE model requires about 15GB of storage space even with 4-bit quantization.
## ModelBest Uses LES Technology
ModelBest introduced LES (look-ahead expert scheduling) to improve decode speed and memory usage.
## Qualcomm Optimizes Hexagon NPU
Qualcomm's redesigned Hexagon NPU expands on-chip shared memory by 50% and adds an Element Accelerator.
## Rising Storage Costs Challenge Vendors
TrendForce notes that flagship phone memory configurations will trend toward 12GB in 2026, with 16GB configurations squeezed.
## Power Consumption Targets
Vivo aims for under 500 milliamps for 30B MoE models by 2028, down from 800 milliamps for 3B models.
## 24-Month Chip Development Lag
Smartphone chips take about 24 months from planning to launch, creating uncertainty for 30B MoE deployments.
## Key takeaway

Smartphone makers are racing to deploy 30B-class AI models on devices, but face memory and power constraints as storage costs rise.