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
Qwen3 30B vs Gemma 4 26B on RTX 3090: Full VRAM Showdown
Head-to-head benchmark of Qwen3 30B and Gemma 4 26B on a single RTX 3090 with full VRAM available. Real Ollama API measurements — generation speed, prefill speed, and which model wins at each task.
Jetson Thor vs Jetson Orin 64GB: Local LLM Benchmark Notes
Hands-on local LLM benchmark notes from Jetson Thor and Jetson Orin 64GB, including Qwen model setup, latency, tokens per second, and practical deployment advice.
LocateAnything-3B Benchmark: RTX 3090 vs Jetson AGX Thor
Real hardware benchmark of NVIDIA's LocateAnything-3B vision-language model across RTX 3090 and Jetson AGX Thor — inference speed, memory, and deployment conclusions for edge AI.
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.
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.
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 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.
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.
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.
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.
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.
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.
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.