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 views3 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
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
RTX 3060 + 3070，真的能拉動 Qwen 3.8 Next Flash？｜Strata 實測
RTX 3060 + 3070，真的能拉動 Qwen 3.8 Next Flash？｜Strata 實測
2.4K views1 month ago
YouTubeStar_Owal
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
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
8:44
Qwen 3.8 Flash Next Tested: Is it Actually Fast?
14.2K views2 months ago
YouTubeDEEPTECH AI LABS
9:07
Qwen3.8-Flash and Qwen3.8- Flash-Next : Everything You Need to Know , Qwen 4 Architecture Preview
10.6K views2 months ago
YouTubeAI WITH Rithesh
6:42
Qwen 4 Is Coming! Qwen3.8 MoE Reveals the Next Architecture
7.8K views2 months ago
YouTubeLocal Agent Lab
0:30
Same 12GB GPU: 2.8 vs 30 Tokens a Second (Qwen 27B vs a 125B Model)
2 days ago
YouTubeCompute Clearly
9:49
Best Local LLM for 12GB VRAM: Can a 125B Model Beat Qwen 27B?
2 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
13:28
Frontier AI at Home — It's Actually Here Now
1K views2 months ago
YouTubeSignal Coders
18:00
Qwen 3.8 27B or Flash Next on Strata? Which one your GPU should run..
719 views3 days ago
YouTubeKernelBrief
17:24
Skip the RTX 3090: Every Way to Run Local AI Under $1,000
8 views1 day ago
YouTubeA-Qube
18:10
Qwen3.8-Flash-Next on AMD Strix Halo: Halogen, N-grams and Benchmarks
88.1K views2 months ago
YouTubeDonato Capitella
32:06
I Ran Qwen 3.8 Flash Next (Qwen 4) on CPU Only
22K views2 months ago
YouTubeLaxmi Kant | KGP Talkie
47:38
Why Qwen3.8 Flash Is So Cheap to Run 0 to 96GB VRAM Explained and Tested!
20K views2 months ago
YouTubeLukasz Gawenda
3:29
Strata on 7 GPUs: Which Card Runs Local AI Fastest? (Full Benchmark)
16.9K views1 month ago
YouTubeTech-Practice
11:45
You Don't Need a $2,000 GPU for Local AI Anymore
4 views2 days ago
YouTubeSanchit Gogna
13:39
Qwen3.8-Flash-Next 125B: 60 TPS MLX vs 30 TPS llama.cpp on M5 Max 🚀
23.2K views2 months ago
YouTubeExecute Automation
7:25
I Ran QWEN 3.8 FLASH NEXT 125B On My 12GB GPU?! (The 27B’s Game Wouldn’t Even Start)
1.2K views2 weeks ago
YouTubeVitoMind
7:53
Qwen 125B Runs on a 12GB RTX 3060 (Buy RAM Instead)
3 views1 month ago
YouTubeCOLDPATH
9:53
You Don't Need 128GB to Run the Best Local AI Model (What You Actually Need)
4 views2 days ago
YouTubeAI Fusion
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
10:24
Running Qwen 3.8 Flash Next on a $1000 Local AI Build with Strata
128.7K views1 month ago
YouTubeDigital Spaceport
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 views6 hours ago
YouTubeAgenticEngineering
See more
Static thumbnail place holder
You may also want to search