Bijan Bowen

Bijan Bowen

打开 YouTube 频道 ↗ Star on GitHub
Liquid LFM2.5-8B First Test – An On-Device MoE Model!
2026-06-18 暂无字幕
OpenRouter Fusion First Test – Does THIS Beat Claude Fable?
2026-06-16 暂无字幕
Diffusion Gemma First Look & Demo – A BIG Step for Local AI Models!
Google发布Diffusion Gemma模型，通过并行生成机制显著提升本地AI推理效率与硬件利用率
2026-06-14 · 5865 字
GLM-5.2 Is INSANE – Is This the BEST New Open Source Model?
2026-06-13 暂无字幕
Kimi K2.7 Code Is HERE – Is THIS the Best Open Coding Model Yet?
评测Kimi K2.7 Code模型，重点分析其Token效率提升、定价策略及Neon OS桌面环境构建能力。
2026-06-12 · 9853 字
Claude Fable 5 Ultimate Test - Is THIS The Closest Thing to AGI?
2026-06-11 暂无字幕
Claude Fable 5 Is INSANE – Hands-On With the BEST Model Yet!
评测Anthropic发布的Claude Haiku 5模型，对比其作为Mythos 5消费版的定位、定价及初步性能测试。
2026-06-09 · 8262 字
MiniMax M3 Is HERE – Could THIS Be the Best Open Source Model Yet?
2026-06-09 暂无字幕
Kombai Hands-On Test – AI Design Engineer in Cursor!
深度实测Kombai：在Cursor中通过AI设计工程师将创意直接转化为前端代码的完整工作流
2026-06-08 · 6135 字
Nemotron 3 ULTRA First Look & Test – NVIDIA’s LARGEST Model Yet!
2026-06-06 暂无字幕
Gemma 4 12B Is INSANE – Is THIS the BEST Local Coding Model Yet?
实测Gemma 4 12B本地编程能力，通过多项复杂任务验证其是否成为最佳紧凑型代码模型
2026-06-03 · 3876 字
Qwen3.7 Plus First Test – Hands-On With Alibaba’s Mid-Sized Qwen Model!
实测阿里Qwen3.7 Plus模型，涵盖代码生成、游戏模拟及前端交互等多场景性能表现
2026-06-03 · 3877 字
Step 3.7 Flash First Look & LOCAL Test – A VERY Creative Model!
评测Stepfun AI发布的Step 3.7 Flash开源模型，在Mac Studio M3 Ultra上进行本地部署与BrowserOS基准测试。
2026-06-01 · 7563 字
Unstract First Look & Local Setup – Open-Source AI Document Extraction!
Unstract开源平台本地部署全流程与多场景AI文档提取实战演示
2026-05-29 · 4044 字
Claude Opus 4.8 Is HERE – Is THIS the Best Model Yet?
深度实测Claude Opus 4.8，通过浏览器、游戏、3D模拟等全场景测试验证其是否成为当前最强模型
2026-05-29 · 3153 字
Bonsai Image LOCAL Test & Install – A 1-Bit Image Generation Model!
博主实测Prism ML的Bonsai Image模型，详解Windows安装及1-bit/3-bit生成效果
2026-05-27 · 4163 字
MiniCPM5 1B First Look & Test – Is This a USABLE 1B Model?
2026-05-26 暂无字幕
Docker Sandboxes Hands-On Guide – A Safe Space for AI Agents!
Docker Sandboxes 通过隔离环境让 AI Agent 安全自主执行操作，本文演示 Mac 端安装与网络策略配置。
2026-05-22 · 7852 字
Gemini 3.5 Flash Is INSANE – Is THIS a Frontier Coding Model?
实测Gemini 3.5 Flash在代码生成、3D模拟及多模态任务中的极限表现与前沿能力验证
2026-05-20 · 5422 字
Cursor Composer 2.5 Is VERY Good – Does THIS Beat GPT & Opus?
实测Cursor Composer 2.5在多项编程任务中表现优异，挑战GPT与Opus的地位
2026-05-20 · 5088 字
Qwen3.7 Max First Test – Hands-On With Alibaba’s SMARTEST Model!
2026-05-19 暂无字幕
Grok Build + Grok 4.3 FULL Test – xAI’s Claude Code & Codex Competitor!
2026-05-15 暂无字幕
SenseNova U1 First Test – A New Kind of Open Source Image Model!
测试SenseNova U1在云端和DGX Spark本地的图像生成能力，涵盖趣味信息图与严肃硬件对比。
2026-05-13 · 5300 字
Ernie 5.1 First Look & Test – Is THIS the Most Creative Model Yet?
2026-05-11 暂无字幕
Casual RTX 6000 Pro AI Build – NEW Local AI Training Setup!
博主开箱并组装一台搭载 PNY RTX 6000 Pro 的复古风本地 AI 训练主机，展示硬件细节与安装过程。
2026-05-07 · 5313 字
Mistral Medium 3.5 First Test – A 128B Dense Open-Source Model!
评测Mistral Medium 3.5：128B密集多模态模型的本地与API性能实测
2026-05-05 · 9955 字
Local AI Web Scraping with n8n & Oxylabs – Workflow Breakdown!
2026-05-03 暂无字幕
Qwen3.6 Max First Test – Hands-On With Alibaba’s SMARTEST Model!
2026-05-02 暂无字幕
HY3 Preview FULL Test – Hands-On With Tencent’s Next-Gen Model!
深度评测腾讯HY3预览版模型，聚焦其Agent能力、架构特性及Browser OS实战表现。
2026-05-01 · 11820 字
Xiaomi MiMo V2.5 Pro Full Test – Is THIS The BEST Open Source Model?
深度评测Xiaomi MiMo V2.5 Pro开源模型，从基准测试到BrowserOS实战的全方位性能解析
2026-04-28 · 2836 字
GPT-5.5 Pro Is INSANE – Hands-On With OpenAI’s BEST Model!
实测OpenAI GPT-5.5 Pro：深度解析其高昂定价、极致性能与复杂游戏开发能力
2026-04-27 · 3578 字
GPT-5.5 Is HERE – Is THIS the Best Model Yet?
实测GPT-5.5在代码生成、模拟仿真及浏览器操作中的表现，揭示其能力边界与局限
2026-04-24 · 3402 字
DeepSeek V4 Is HERE – Testing the LARGEST Open Source Model Ever!
实测DeepSeek V4开源模型，涵盖代码、仿真及多场景性能验证
2026-04-24 · 4305 字
Qwen3.6 27B Is INSANE – Is This a LOCAL Claude Opus Competitor?
2026-04-23 暂无字幕
Grok 4.3 Beta First Test – Is THIS a Frontier Model Competitor?
2026-04-22 暂无字幕
ChatGPT Images 2.0 Is INSANE – Testing OpenAI’s New Image Model!
深度实测OpenAI ChatGPT Images 2.0，涵盖海报、游戏素材、图像编辑及复杂逻辑推理等多场景表现
2026-04-22 · 4858 字
Kimi K2.6 Code Is INSANE – Testing The NEW Kimi Coding Model!
2026-04-22 暂无字幕
Meta Muse Spark Contemplating – A GPT Pro & Deep Think Competitor?
2026-04-22 暂无字幕
Claude Opus 4.7 Is INSANE – Is This the Best Model Yet?
深度实测Claude Opus 4.7，通过代码、游戏与多模态任务验证其是否成为最强模型
2026-04-22 · 4129 字
Meta AI Muse Spark Is HERE – Testing Meta’s New Frontier Model!
实测Meta最新前沿模型Muse Spark，通过编程、游戏模拟及多模态任务验证其真实能力
2026-04-22 · 3655 字
VoxCPM2 TTS First Test – LOCAL Voice Cloning & Multilingual TTS!
2026-04-22 暂无字幕
Qwen3.6 35B-A3B Full Test – Is THIS the Best LOCAL Model Yet?
2026-04-22 暂无字幕
Gemma 4 Small Models Are INSANE – E2B & E4B Hands-On Testing!
实测Gemma 4小模型E2B与E4B变体，通过浏览器、3D游戏及多模态任务验证其本地性能极限
2026-04-22 · 3476 字
Kimi K2.6 Is HERE – Is This the BEST Open Source Model Yet?
深度实测Kimi K2.6开源模型，通过编程、3D模拟及多模态任务验证其是否成为最强开源AI
2026-04-22 · 8878 字
Prism is open source · ⭐ Star on GitHub · about