MultimodalFlow
Technical publication · Edge AI · Multimodal

Multimodal AI Deployment, Edge Vision, and Real-time 3D Perception

MultimodalFlow is a technical publication about multimodal AI, computer vision, edge AI deployment on Jetson devices, TensorRT optimization, stereo depth estimation, thermal-RGB fusion, and industrial inspection systems.

Featured Articles

Latest Articles

View all articles

Qwen3.8-27B Benchmarked: 58 tok/s on an RTX 3090 at Q4, 4.1 tok/s on a Jetson Thor at BF16

The same 27B model, two machines, a 14× speed gap. Real numbers from an RTX 3090 (Ollama Q4_K_M) and a Jetson AGX Thor (vLLM BF16) — how much of the gap is quantization, how much is memory bandwidth, and what Thor wins back under concurrency.

Qwen3.8benchmarkRTX 3090

2×Jetson Thor for DeepSeek-V4-Flash-NVFP4: QSFP28 Preflight and Real Blockers

A preflight test for running nvidia/DeepSeek-V4-Flash-NVFP4 across two Jetson Thor systems. The result: SGLang/vLLM containers are present, but QSFP28 IP configuration, disk capacity, and Jetson aarch64 NVFP4 maturity must be solved before downloading and launching the model.

DeepSeek-V4-FlashNVFP4Jetson Thor

Can DeepSeek's New V4-Flash-0731 Run on Jetson Thor? The 284B MoE Edge Boundary

DeepSeek-V4-Flash-0731 is a recent MIT-licensed open-weight model with 284B total parameters, 13B activated parameters, and 1M context. This post checks whether it fits Jetson Thor and outlines a practical benchmark path.

DeepSeek-V4DeepSeek-V4-FlashJetson Thor

DeepSeek V4 Flash NVFP4 on 2×Jetson Thor, Debug Log 1: SGLang Reaches DeepGEMM

A practical debug log for trying nvidia/DeepSeek-V4-Flash-NVFP4 across two Jetson Thor systems: QSFP28 setup, model download, SGLang nightly, KV cache fallback, Docker runtime fixes, and the final DeepGEMM HyperConnection sm110 blocker.

DeepSeek-V4DeepSeek-V4-FlashNVFP4

Can Qwen3.8-Max Run on Jetson Thor? The 2.4T Frontier Model vs Edge Hardware

Qwen3.8-Max is Alibaba's latest Qwen flagship, described as a 2.4T-parameter model for coding and complex work. This post checks the Jetson Thor boundary and explains why Qwen3-8B or Qwen3.6 models are the realistic local benchmark targets.

Qwen3.8-MaxQwen3-8BJetson Thor

Jetson T2000 vs T3000 vs Orin: 2026 Edge AI Hardware Guide

How should you choose between NVIDIA Jetson T2000, T3000, AGX Thor, Orin, and desktop GPUs for edge AI in 2026? A practical guide for LLMs, VLMs, robotics, and multimodal deployment.

JetsonT2000T3000

MiniMax H3 on Jetson AGX Thor: Early Public Benchmark Plan for FL2VA, Ref2VA, and INT8 ConvRot

A reproducible MiniMax H3 benchmark protocol on Thor-JD covering FL2VA, Ref2VA, T2VA, INT8 ConvRot, generation time, output validity, memory capacity, and scripts.

MiniMax H3Hailuo 3.0Jetson Thor

Are NVIDIA Jetson AGX Thor LLM Benchmarks Realistic? I Retested on a Live Deployment

NVIDIA has published Jetson AGX Thor vLLM benchmark numbers for Llama, Qwen, DeepSeek, and Qwen2.5-VL. I retested Qwen2.5-7B on a live Thor test machine running model serving, retrieval services, and a desktop environment, then explain why official benchmarks differ from deployment results.

JetsonThorLLM

Jetson AGX Thor + Orbbec 3D Camera: Building a Local Multimodal Robot Inspection System

A hands-on retrospective of a 3D robot inspection project built on NVIDIA Jetson AGX Thor with Orbbec Gemini 345Lg / RealSense D435i, point clouds, YOLO, VLM, RAG, and a local LLM.

JetsonJetson ThorRobotics

Use Cases

Industrial Inspection

Detecting weld defects, fabric flaws, and surface anomalies using thermal-RGB fusion and vision models.

Robotics Perception

Real-time 3D environment understanding via stereo depth and point cloud for mobile robot navigation.

Thermal-RGB Fusion

Combining thermal infrared and visible-light imagery for night-time detection and temperature anomaly alerts.

Edge AI Deployment

Shipping TensorRT-optimized inference pipelines on Jetson AGX Thor, Jetson Orin, and similar edge hardware.

Real-time Point Cloud

Streaming depth-sensor data as live 3D point clouds via Three.js and WebGL in the browser.

Local GPU Inference

Running large language models on consumer GPUs (RTX 3090, etc.) with Ollama and llama.cpp — benchmark data included.

About This Site

MultimodalFlow is run by engineers. Everything published here comes from real hardware tests and production deployment experience — inference tuning on Jetson edge devices, LLM benchmarks on consumer GPUs, and industrial vision inspection systems built for actual production lines. We don't publish unverified spec sheets or vendor PR. Every benchmark article includes the exact commands and raw output so you can reproduce the results yourself. If you're working on edge AI deployment, vision model optimization, or multimodal system integration, the notes and lessons here are for you.
Learn about this site