Skip to content

DEV Community

GINIGEN AI

404 bio not found

Joined on Oct 5, 2026

GINIGEN AI

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

13 min read

GINIGEN AI

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

15 min read

GINIGEN AI

Nov 1

Asymmetric Control for AI Agents: Why the Stop Path Must Be Independent of the Model

#ai #security #agents #architecture

3 min read

GINIGEN AI

Nov 1

Why a Sparse 35B MoE Runs Faster on a CPU Than a Dense 27B Model

#ai #machinelearning #edgeai #llm

5 min read

GINIGEN AI

Oct 31

LFM3-1.7B On-Device: The 256K KV Cache Math, Which GGUF to Ship, and the Safety Test to Run First

#ai #machinelearning #edgeai #quantization

14 min read

GINIGEN AI

Oct 29

From 46M to 325M: An Inference NPU Now Pretrains a Language Model at GPU Quality

#ai #machinelearning #edgeai #npu

2 min read

GINIGEN AI

Oct 26

The Inference Hardware You Already Own Might Train Models Too: A 325M Pretraining Run on an NPU

#ai #machinelearning #edgeai #hardware

3 min read

GINIGEN AI

Oct 23

Chitos on the OWASP Benchmark: 77.8 Youden, on-prem

#security #ai #appsec #benchmark

1 min read

GINIGEN AI

Oct 21

0.1 Bits Per Weight Is Not 0.1 Bits Per Weight: Where the Bytes Go in Sub-2-Bit LLMs

#ai #machinelearning #edgeai #quantization

14 min read

GINIGEN AI

Oct 20

Put the Decision Model Inside the Agent Loop, Not Beside It

#agents #ai #llm #machinelearning

3 min read

GINIGEN AI

Oct 19

LFM2.5-24B-A2B on Your Own Hardware: The RAM, KV Cache and Bandwidth Budget

#ai #machinelearning #edgeai #quantization

11 min read

GINIGEN AI

Oct 12

사라진 명리 비기를 AI로 복원하다: 주명명리(宙明命理) 개발기

#ai #machinelearning #llm #webdev

1 min read

GINIGEN AI

Oct 12

Zero-Token Decisions in the Browser: On-Device Multimodal Classification with EmbeddingGemma 2 and WebGPU

#ai #machinelearning #webgpu #opensource

3 min read

GINIGEN AI

Oct 11

Open Quantum Challenge (OQC): a reproducible, hardware-free quantum benchmark

#quantum #benchmark #opensource #machinelearning

1 min read

GINIGEN AI

Oct 11

One Self-Improving Model, Eleven Number-One Titles: What That Takes

#ai #machinelearning #llm #opensource

2 min read

GINIGEN AI

Oct 6

4-bit GGUF Quality for MoE Models: Why Only 3B of 180B Params Fire, and How to Prove Parity

#ai #llm #quantization #edgeai

7 min read

GINIGEN AI

Oct 6

Building an AI That Refuses to Say "Safe": Reliability Engineering for an Offline Disaster App

#ai #edgeai #llm #android

7 min read

GINIGEN AI

Oct 6

Running a 180B Model on a Laptop With No GPU: How 4-bit GGUF Keeps Full Accuracy

#ai #llm #edgeai #quantization

6 min read

GINIGEN AI

Oct 5

Offline AI on a Phone: Thread Pinning, Lazy Loading, and a Safety Gate That Knows When to Stay Quiet

#ai #android #llm #edgeai

11 min read

loading...