老X99＋96GB DDR3，竟然跑起Qwen3.8 Flash大模型！RTX 3060实测与参数拆解
7:36
老X99＋96GB DDR3，竟然跑起Qwen3.8 Flash大模型！RTX 3060实测与参数拆解
3.2K views4 days ago
bilibili玩客笔记
125B AI on a 12GB RTX 3060?! 73 Tokens/sec on a $420 Old PC
13:13
125B AI on a 12GB RTX 3060?! 73 Tokens/sec on a $420 Old PC
1 views4 days ago
YouTubeGeekLab AI
My RTX 3060 Runs Qwen 3.8 Flash Next 180B at 51 Tokens/sec. Yours Can Too!
8:03
My RTX 3060 Runs Qwen 3.8 Flash Next 180B at 51 Tokens/sec. Yours Can Too!
15.2K views1 month ago
YouTubegAIjin Foundry
1500元显卡真能跑125B？RTX 3060 极限实测千亿 Qwen3.8：三级存储与全避坑指南
5:15
1500元显卡真能跑125B？RTX 3060 极限实测千亿 Qwen3.8：三级存储与全避坑指南
2K views1 month ago
YouTube玩客笔记
Running Qwen 3.8 Flash Next on a $1000 Local AI Build with Strata
10:24
Running Qwen 3.8 Flash Next on a $1000 Local AI Build with Strata
128.7K views1 month ago
YouTubeDigital Spaceport
My RTX 3060 Runs Qwen 3.8 Flash Next 180B at 75.5 Tokens/sec—Yours Can Too! | Strata + Qwen
8:32
My RTX 3060 Runs Qwen 3.8 Flash Next 180B at 75.5 Tokens/sec—Yours Can Too! | Strata + Qwen
10.5K views1 month ago
YouTubegAIjin Foundry
Strata AI: 1-bit Qwen3.8-Flash-Next at 31-37 tok/s on a 12 GB RTX 3060 (devs' Linux test) #Shorts
0:28
Strata AI: 1-bit Qwen3.8-Flash-Next at 31-37 tok/s on a 12 GB RTX 3060 (devs' Linux test) #Shorts
3 days ago
YouTubeGitNova
RTX 3060 + 3070，真的能拉動 Qwen 3.8 Next Flash？｜Strata 實測
2.4K views1 month ago
YouTubeStar_Owal
8:44
Qwen 3.8 Flash Next Tested: Is it Actually Fast?
14.2K views2 months ago
YouTubeDEEPTECH AI LABS
0:30
Same 12GB GPU: 2.8 vs 30 Tokens a Second (Qwen 27B vs a 125B Model)
3 days ago
YouTubeCompute Clearly
14:45
This New llama.cpp Fork Turns Your SSD Into VRAM (22 Tok/s)
1.7K views1 day ago
YouTubeCian Mag
18:00
Qwen 3.8 27B or Flash Next on Strata? Which one your GPU should run..
719 views4 days ago
YouTubeKernelBrief
11:45
You Don't Need a $2,000 GPU for Local AI Anymore
4 views2 days ago
YouTubeSanchit Gogna
18:10
Qwen3.8-Flash-Next on AMD Strix Halo: Halogen, N-grams and Benchmarks
88.1K views2 months ago
YouTubeDonato Capitella
9:49
Best Local LLM for 12GB VRAM: Can a 125B Model Beat Qwen 27B?
3 days ago
YouTubeCompute Clearly
17:24
Skip the RTX 3090: Every Way to Run Local AI Under $1,000
8 views2 days ago
YouTubeA-Qube
47:38
Why Qwen3.8 Flash Is So Cheap to Run 0 to 96GB VRAM Explained and Tested!
20K views2 months ago
YouTubeLukasz Gawenda
6:42
Qwen 4 Is Coming! Qwen3.8 MoE Reveals the Next Architecture
7.8K views2 months ago
YouTubeLocal Agent Lab
16:24
Qwen4 early Architecture Is HERE — Qwen3.8 Flash Next Explained
1.3K views2 months ago
YouTubeLocal Agent Lab
13:28
Frontier AI at Home — It's Actually Here Now
1K views2 months ago
YouTubeSignal Coders
9:53
You Don't Need 128GB to Run the Best Local AI Model (What You Actually Need)
4 views2 days ago
YouTubeAI Fusion
32:06
I Ran Qwen 3.8 Flash Next (Qwen 4) on CPU Only
22K views2 months ago
YouTubeLaxmi Kant | KGP Talkie
3:29
Strata on 7 GPUs: Which Card Runs Local AI Fastest? (Full Benchmark)
16.9K views1 month ago
YouTubeTech-Practice
1:09
Strata runs Qwen3.8-Flash-Next on a gaming PC? #shorts
2 views4 days ago
YouTubeTonyfyp
9:01
DeepSeek V4 Flash on a CPU Only: Viral Hack or Total Trap?
4 days ago
YouTubeRunning Local
15:55
【Strata】5年前のRTX3060で巨大モデルは動く？実測してクラウドAIと比べてみた
700 views2 days ago
YouTubeずんだもんのテック研究所
7:34
PROMETHEVS: Full 510GB DeepSeek on a 12GB GPU at 7.4 tok/s
1 views9 hours ago
YouTubeAgenticEngineering
7:25
I Ran QWEN 3.8 FLASH NEXT 125B On My 12GB GPU?! (The 27B’s Game Wouldn’t Even Start)
1.2K views3 weeks ago
YouTubeVitoMind
7:15
最新版Strata运行Swift 1.5 Flash Next 4卡RTX3080并行 生成速度最高143ts 预填充最高2200ts
363 views2 days ago
bilibiliDenjhang
9:19
【今週のまとめ 11/2〜11/8】12GB PCで動くローカルAI総点検！Kimi・MiMo・Ollama最新アプデ【ずんだもん解説】
2K views6 days ago
YouTubeAIの歩き方
See more
Static thumbnail place holder