2.85x Speedup on MoE Models | What the Industry Got Wrong About Scaling
7:52
2.85x Speedup on MoE Models | What the Industry Got Wrong About Scaling
6 views4 months ago
YouTubeSaral Research Paper
Stop One-Shotting MoE Models - Why They Fail and What Works
12:46
Stop One-Shotting MoE Models - Why They Fail and What Works
42.6K views6 months ago
YouTubeProtorikis
+90% speed for all LLM (MoE) with n-cpu-moe
14:00
+90% speed for all LLM (MoE) with n-cpu-moe
1.6K viewsSep 8, 2025
YouTubeCodeRocks & Apprendre
Phison SSDs For 120B Models in AI Playground
4:43
Phison SSDs For 120B Models in AI Playground
1.2K views2 months ago
YouTubeIntel Technology
DFlash on GTX 1060: Can Dense AI Models Cheat VRAM Like MoE?
11:30
DFlash on GTX 1060: Can Dense AI Models Cheat VRAM Like MoE?
40.6K views5 months ago
YouTubeCodacus
The Problem With Dense Models That MoE Actually Solves
7:26
The Problem With Dense Models That MoE Actually Solves
718 views7 months ago
YouTubeAI Explained in 5 Minutes
Kimi 3 Internals: Scaling Muon for Efficient Large Language Model Training. Latent MoE, MoBA,AttnRes
20:58
Kimi 3 Internals: Scaling Muon for Efficient Large Language Model Training. Latent MoE, MoBA,AttnRes
663 views2 months ago
YouTubeByte Goose AI.
9:09
How to Run Massive AI Models Locally (Quantization & LoRA)
2 views4 months ago
YouTubeTutorialsArena - MCQs, Coding Interviews & More!
25:38
Efficient MoE Pre-training at Scale on AMD GPUs With TorchTitan -Liz Li & Yanyuan Qin, Matthias Reso
412 views11 months ago
YouTubePyTorch
5:15
FreeToken Is INSANE — Run Giant AI Models Locally
9.1K views1 month ago
YouTubeCodedigipt
14:25
Why Frontier MoE Fails on Consumer GPUs — FreeToken Architecture Explained
300 views1 month ago
YouTubeAgenticEngineering
22:39
Research Paper Deep Dive - The Sparsely-Gated Mixture-of-Experts (MoE)
3.4K viewsJun 22, 2022
YouTube650 AI Lab
6:47
How 120B+ Parameter Models Run on One GPU (The MoE Secret)
2K viewsAug 16, 2025
YouTubeShane | LLM Implementation
3:51
4bit vs Full Precision: Which is Right for You?
1.1K views2 months ago
YouTubeSebastian Buzdugan
10:20
Dense vs MoE: The Architecture Behind Modern AI
536 views4 months ago
YouTubeHarris Oldroyd
11:36
Running a 22GB AI Model on a 6GB GPU, FAST (llama.cpp Guide)
21.8K views2 months ago
YouTubeCloud Codes
6:59
How To Get LOWER PROCESSES on Windows! (LOWER INPUT DELAY & MORE FPS)
23.5K views5 months ago
YouTubeSynez
2:29
Ultimate Process Lowering Guide 🔧 | Decrease Input Delay + Boost Fps in Windows
6.2K views3 months ago
YouTubeRisxn
1:00:14
CPU LLM #1: The Memory Layout That Makes CPU LLMs Faster.
1.4K viewsJun 26, 2025
YouTubeANTSHIV ROBOTICS
2:35
Ultimate Process Lowering Guide 🔧 | Decrease Input Delay + Boost Fps in Windows
10.2K views4 months ago
YouTubeRisxn
20:33
How Fast Can One RTX 3060 Actually Run 35B (llama.cpp enhancement)?
17.2K views1 month ago
YouTubeCodacus
5:05
Best NVIDIA Settings for Counter-Strike 2 (MAX FPS + Lowest Input Lag)
4.5K views3 months ago
YouTubePrefire
4:40
How to Compress Images with ChatGPT While Keeping CRISP Quality
355 views9 months ago
YouTubeAsapGuide
13:03
Running NVIDIA Nemotron-3-Ultra-550B-A55B(Q4K_S) — RTX PRO 6000
1.2K views4 months ago
YouTubeksh3
8:45
Change this setting in LM Studio to run MoE LLMs faster.
36.3K viewsSep 5, 2025
YouTubeLearn Meta-Analysis
9:38
How to DOUBLE the LM Studio AI Inference Speed with These HIDDEN Settings
19.8K views8 months ago
YouTubeAsapGuide
6:27
Reduce PROCESSES on Windows in Just 5 Minutes (Faster PERFORMANCE) 2025
10.3K views11 months ago
YouTubeCrown GEEK
11:10
Best CPU Optimization for Gaming in 2026 (CMD, Registry, Process Lasso, Low Latency Guide)
7.7K views8 months ago
YouTubeThe Software Guy
5:27
Microsoft BitNet: Shocking 100B Param Model on a Single CPU
15.2K viewsOct 26, 2024
YouTubeMervin Praison
2:01
*ULTIMATE* Process Lowering Guide 🔧 (Lower Input Delay + Boost FPS Instantly)
2.1K views10 months ago
YouTubeRisxn Tweaks
See more
Static thumbnail place holder