produced by Classmethod

# LLM articles

Large Language Modelの略称で、GPT-3やChatGPTなどの大規模な言語モデルを指します。

必見の記事

I tried running Gemma 4 locally on a MacBook (16GB) — from model selection and UI setup with Ollama to practical project use

2026.04.09

注目の記事

Tried to run Gemma 4 locally at its limit (31b q8) on M1 Max 64GB

小渕ヒューゴ

2026.04.06

注目の記事

I tried running Gemma 4 on DGX Spark and benchmarked Japanese and multimodal capabilities

森茂洋 / Hiroshi Morishige

2026.04.03

ちょっと話題の記事

I tried running SAM 3.1 on DGX Spark for zero-shot object detection

森茂洋 / Hiroshi Morishige

2026.04.01

I tried fine-tuning NVIDIA Cosmos-Reason2-8B on DGX Spark for PPE detection

森茂洋 / Hiroshi Morishige

2026.03.31

I tried making a 3D digital twin of DGX Spark from smartphone videos

森茂洋 / Hiroshi Morishige

2026.03.28

話題の記事

I tried TurboQuant and RotorQuant on DGX Spark

森茂洋 / Hiroshi Morishige

2026.03.27

殿堂入り記事

After 2 Months of Using DGX Spark: "Jobs It's Good At" and "Jobs It's Not Good At"

森茂洋 / Hiroshi Morishige

2026.03.24

I picked up 7 interesting sessions from GTC 2026 on-demand sessions

森茂洋 / Hiroshi Morishige

2026.03.21

ちょっと話題の記事

I tried running NVIDIA NemoClaw on DGX Spark

森茂洋 / Hiroshi Morishige

2026.03.21

When I tried three subjects with Godot and Codex, I could see the strength of the initial output and the burden of manual verification

越井琢巳 (Koshii Takumi)

2026.03.18

ちょっと話題の記事

I tried running NVIDIA Nemotron 3 Super on DGX Spark

森茂洋 / Hiroshi Morishige

2026.03.12

I tried real-time monitoring of video with VSS Event Reviewer

森茂洋 / Hiroshi Morishige

2026.03.10

I tried the Warehouse Blueprint of VSS 3.0.0 EA on DGX Spark

森茂洋 / Hiroshi Morishige

2026.03.08

ちょっと話題の記事

I tried imitation learning on SO-ARM101 with LeRobot's ACT

森茂洋 / Hiroshi Morishige

2026.03.07

I tried running NVIDIA Cosmos world foundation models on DGX Spark

森茂洋 / Hiroshi Morishige

2026.03.06

注目の記事

Building a Private LLM Environment (Qwen 3.5-4B) on AWS That Can Be Used from Both Smartphones and PCs

越井琢巳 (Koshii Takumi)

2026.03.05

I tried Dreambooth LoRA fine-tuning of FLUX.1 on DGX Spark

森茂洋 / Hiroshi Morishige

2026.03.03

"Can You See What's Inside?" Examining LLM Steerling-8B and Running It on DGX Spark

森茂洋 / Hiroshi Morishige

2026.03.02

I tried assembling the SO-ARM101 and doing teleoperation with LeRobot

森茂洋 / Hiroshi Morishige

2026.03.01

I tried running a video search AI agent on DGX Spark (VSS Agent)

森茂洋 / Hiroshi Morishige

2026.02.26

Tried training full-layer LoRA including Mamba-2 on Nemotron 9B × Megatron-Bridge using NVIDIA Brev H100

森茂洋 / Hiroshi Morishige

2026.02.25

ちょっと話題の記事

I tried reinforcement learning for a robot arm with DGX Spark (Isaac Sim + Isaac Lab + SO-ARM101)

森茂洋 / Hiroshi Morishige

2026.02.24

I tried teaching Classmethod's culture CLP to Nemotron 9B-v2

森茂洋 / Hiroshi Morishige

2026.02.23

I tried improving RAG accuracy of Nemotron 9B-v2 with NTA FAQ × RAFT

森茂洋 / Hiroshi Morishige

2026.02.22

I tried deploying Nemotron 9B-v2-Japanese to SageMaker Tokyo Region with a VPC closed network configuration

森茂洋 / Hiroshi Morishige

2026.02.21

注目の記事

I tried NVIDIA's official Japanese-enhanced LLM Nemotron 9B-v2-Japanese in various cases

森茂洋 / Hiroshi Morishige

2026.02.19

I tried real-time analysis of camera footage with the Live VLM WebUI on DGX Spark

森茂洋 / Hiroshi Morishige

2026.02.17

I tried fine-tuning Nemotron 3 Nano in Japanese on DGX Spark

森茂洋 / Hiroshi Morishige

2026.02.16

Using Structured Outputs with Amazon Bedrock Batch Inference Too: Stabilizing AI Output

2026.02.16

話題の記事

I tried connecting two DGX Sparks together to test distributed inference of large-scale models

森茂洋 / Hiroshi Morishige

2026.02.13

ちょっと話題の記事

I tried building a local code completion environment in VS Code using DGX Spark × Continue.dev

森茂洋 / Hiroshi Morishige

2026.02.11

Build a Remote Desktop Environment on DGX Spark (RustDesk + Tailscale)

森茂洋 / Hiroshi Morishige

2026.02.09

ちょっと話題の記事

What Can You Do with DGX Spark? I Organized the Official Playbook

森茂洋 / Hiroshi Morishige

2026.02.08

注目の記事

I tried again to run Claude Code + Ollama locally on the 128GB memory of DGX Spark

森茂洋 / Hiroshi Morishige

2026.02.07

殿堂入り記事

I tried to organize the local LLM situation in 2026

森茂洋 / Hiroshi Morishige

2026.01.28