Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
edgeai
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
A 763B MoE on a 12 GB GPU: Our Speed Ceiling Versus What Strata Reports, and What Closes the Gap
GINIGEN AI
GINIGEN AI
GINIGEN AI
Follow
Nov 3
A 763B MoE on a 12 GB GPU: Our Speed Ceiling Versus What Strata Reports, and What Closes the Gap
#
ai
#
machinelearning
#
edgeai
#
llm
Comments
Add Comment
13 min read
Moderation
Pinning NPU cores on RK3588 buys you 5% — and costs the big model 10%
Anguo
Anguo
Anguo
Follow
Nov 3
Pinning NPU cores on RK3588 buys you 5% — and costs the big model 10%
#
rockchip
#
rknn
#
benchmark
#
edgeai
Comments
Add Comment
2 min read
Moderation
System design for physical AI: from a defect image to the chamber that drifted
Umar Bilal
Umar Bilal
Umar Bilal
Follow
Nov 3
System design for physical AI: from a defect image to the chamber that drifted
#
ai
#
architecture
#
edgeai
#
ontology
Comments
Add Comment
5 min read
Moderation
RK3576 vs RK3568: Which Rockchip SoC Is Right For Your Embedded Edge Project?
Rocky Gao
Rocky Gao
Rocky Gao
Follow
Nov 3
RK3576 vs RK3568: Which Rockchip SoC Is Right For Your Embedded Edge Project?
#
embedded
#
rockchi
#
edgeai
#
linux
2
 reactions
Comments
Add Comment
3 min read
Moderation
A 763B MoE at "2 Bits": Where the Bytes Really Go in the GSQ-RCO GGUFs, and Why 100% Recovery Sits Inside the Noise
GINIGEN AI
GINIGEN AI
GINIGEN AI
Follow
Nov 2
A 763B MoE at "2 Bits": Where the Bytes Really Go in the GSQ-RCO GGUFs, and Why 100% Recovery Sits Inside the Noise
#
ai
#
machinelearning
#
edgeai
#
quantization
Comments
Add Comment
15 min read
Moderation
10 RKNN models benchmarked on RK3588 — and the fastest one is cheating onto the CPU
Anguo
Anguo
Anguo
Follow
Nov 2
10 RKNN models benchmarked on RK3588 — and the fastest one is cheating onto the CPU
#
rockchip
#
rknn
#
benchmark
#
edgeai
Comments
Add Comment
4 min read
Moderation
RK3588 INT8, measured: 1.96 on YOLOv8n, 1.4 on YOLO11n — plus OCR joins the bench
Anguo
Anguo
Anguo
Follow
Nov 2
RK3588 INT8, measured: 1.96 on YOLOv8n, 1.4 on YOLO11n — plus OCR joins the bench
#
rockchip
#
rknn
#
benchmark
#
edgeai
Comments
Add Comment
2 min read
Moderation
From 46M to 325M: An Inference NPU Now Pretrains a Language Model at GPU Quality
GINIGEN AI
GINIGEN AI
GINIGEN AI
Follow
Oct 29
From 46M to 325M: An Inference NPU Now Pretrains a Language Model at GPU Quality
#
ai
#
machinelearning
#
edgeai
#
npu
Comments
Add Comment
2 min read
Moderation
AquaAirX MATSYA Challenge 2026: Phase 1 Idea & Solution Report
Pavan Kumar Sadashiv
Pavan Kumar Sadashiv
Pavan Kumar Sadashiv
Follow
Oct 26
AquaAirX MATSYA Challenge 2026: Phase 1 Idea & Solution Report
#
hackathon
#
marine
#
iot
#
edgeai
Comments
Add Comment
12 min read
Moderation
MATSYA-Node: Resolving the 3 Critical Field Questions (Weight, Camera Placement & Net Drop Detection)
Pavan Kumar Sadashiv
Pavan Kumar Sadashiv
Pavan Kumar Sadashiv
Follow
Oct 26
MATSYA-Node: Resolving the 3 Critical Field Questions (Weight, Camera Placement & Net Drop Detection)
#
edgeai
#
iot
#
fisheries
#
hackathon
Comments
Add Comment
5 min read
Moderation
MATSYA-Node: Complete System Architecture, Hardware Selection & Working Mechanism
Pavan Kumar Sadashiv
Pavan Kumar Sadashiv
Pavan Kumar Sadashiv
Follow
Oct 26
MATSYA-Node: Complete System Architecture, Hardware Selection & Working Mechanism
#
iot
#
edgeai
#
hardware
#
marine
Comments
Add Comment
8 min read
Moderation
MATSYA-Node: Our 4-Tier Core System Architecture to Win MATSYA 2026
Pavan Kumar Sadashiv
Pavan Kumar Sadashiv
Pavan Kumar Sadashiv
Follow
Oct 26
MATSYA-Node: Our 4-Tier Core System Architecture to Win MATSYA 2026
#
architecture
#
iot
#
edgeai
#
marine
Comments
Add Comment
5 min read
Moderation
Stopping KV Secrets Leaks in Edge AI with Cloudflare Workers
LeoJulieta
LeoJulieta
LeoJulieta
Follow
Oct 27
Stopping KV Secrets Leaks in Edge AI with Cloudflare Workers
#
cloudflare
#
kv
#
edgeai
#
english
Comments
Add Comment
4 min read
Moderation
The Rise of Small Language Models: Why Smaller is Better for the Future of AI
Mecky Alvin Tanuwidjaya
Mecky Alvin Tanuwidjaya
Mecky Alvin Tanuwidjaya
Follow
Oct 24
The Rise of Small Language Models: Why Smaller is Better for the Future of AI
#
ai
#
machinelearning
#
edgeai
#
softwareengineering
Comments
Add Comment
3 min read
Moderation
Liquid Neural Networks: The AI That Adapts on the Fly
nizover
nizover
nizover
Follow
Oct 24
Liquid Neural Networks: The AI That Adapts on the Fly
#
liquidneuralnetworks
#
edgeai
#
robotics
#
machinelearning
Comments
Add Comment
1 min read
Moderation
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account