How to Save 80% VRAM using INT4 and AWQ Quantization
1:04
How to Save 80% VRAM using INT4 and AWQ Quantization
58 views1 week ago
YouTubeBreaking Divide
How to Quantize an LLM with GGUF or AWQ
26:21
How to Quantize an LLM with GGUF or AWQ
13.9K viewsOct 3, 2023
YouTubeTrelis Research
What is AWQ-INT4? Understanding Quantization Levels
1:00
What is AWQ-INT4? Understanding Quantization Levels
1 week ago
YouTubeBreaking Divide
AWQ for LLM Quantization
20:40
AWQ for LLM Quantization
12.9K viewsOct 25, 2023
YouTubeMIT HAN Lab
SAW-INT4: 4-Bit KV-Cache Quantization for LLMs
5:05
SAW-INT4: 4-Bit KV-Cache Quantization for LLMs
24 views1 month ago
YouTubeAI Research Roundup
AI Model Quantization: The Complete Guide — FP32 to Q4_K_M
4:47
AI Model Quantization: The Complete Guide — FP32 to Q4_K_M
49 views3 months ago
YouTubeMichel Laclé
LLM Quantization Techniques Explained - GPTQ AWQ GGUF HQQ BitNet
59:04
LLM Quantization Techniques Explained - GPTQ AWQ GGUF HQQ BitNet
584 views10 months ago
YouTubeJoydeep Bhattacharjee
30:14
LLM Quantization Explained: GPTQ, AWQ, QLoRA, GGUF and More
1.2K views2 months ago
YouTubeTales Of Tensors
25:26
Quantize LLMs with AWQ: Faster and Smaller Llama 3
7.2K viewsApr 26, 2024
YouTubeAI Anytime
11:11
Day 65/75 LLM Quantization Techniques [GPTQ - AWQ - BitsandBytes NF4] Python | Hugging Face GenAI
1.4K viewsApr 16, 2024
YouTubeFreeBirds Crew - Data Science and GenAI
22:49
Double Inference Speed with AWQ Quantization
3.4K viewsSep 26, 2023
YouTubeTrelis Research
AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration | GetMobile: Mobile Computing and Communications
Jan 21, 2025
acm.org
0:51
TinyChat Computer running Llama2-7B Jetson Orin Nano. Key technique: AWQ 4bit quantization.
3.9K viewsApr 16, 2024
YouTubeMIT HAN Lab
2:12:21
LLM Fine-Tuning 12: LLM Quantization Explained( PART 1) | PTQ, QAT, GPTQ, AWQ, GGUF, GGML, llama.cpp
7.7K views9 months ago
YouTubeSunny Savita
9:57
What is LLM Quantization ?
3.2K viewsMar 19, 2025
YouTubeNew Machina
18:57
MLSys'24 Best Paper - AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
4.5K viewsJun 6, 2024
YouTubeMIT HAN Lab
5:30
Quantization Explained Why INT4 Powers Edge LLMs — Gemma Series Part 5
6 days ago
YouTubeThe Stack Underflow
3:21:13
LLM Fine-Tuning 13: LLM Quantization Explained (PART 2) | PTQ, QAT, GPTQ, AWQ, GGUF, GGML, llama.cpp
5.1K views8 months ago
YouTubeSunny Savita
0:24
The Trauma Code: K-Drama Highlights and Insights
2.2K views3 months ago
TikTokkdram_awq
0:25
passando vergonha #fyp #foryou #rdr2 #superlinda #dance
12.4K views3 months ago
TikTokawq.sim
12:10
Optimize Your AI - Quantization Explained
465.1K viewsDec 28, 2024
YouTubeMatt Williams
23:12
[LLMs inference] quantization 量化整体介绍（bitsandbytes、GPTQ、GGUF、AWQ）
12.1K viewsJul 21, 2024
bilibili五道口纳什
8:14
LLM 양자화 & 경량화 완벽 가이드: 70B 모델을 4GB로 압축하는 마법! GPTQ, AWQ, GGUF 총정리
807 views5 months ago
YouTubeDoYouKnow
0:48
السامري السعودي: رايح بيشه وترندات جديدة
142.1K viewsDec 5, 2024
TikTokawq_88
10:51
AWQ大模型量化INT4比FP16 推理快2倍，GPU内存1/3
4.3K viewsNov 4, 2023
bilibili小工蚁创始人
0:28
#طرب #لعب #رايح #رايح_بيشه #سامري #سامري_طرب #سامري_ثقيل #السعودية #الرياض #اكسبلور_تيك_توك #ترند #ترند_تيك_توك
310.3K viewsMay 22, 2024
TikTokawq_88
15:51
Which Quantization Method is Right for You? (GPTQ vs. GGUF vs. AWQ)
39.4K viewsNov 23, 2023
YouTubeMaarten Grootendorst
2:08
#طرب #لعب #سامري #سامري_دواسر #سامري_ثقيل #السعودية #الرياض #رايح #رايح_بيشه #بيشه #الطائف #وادي_الدواسر #الافلاج #الخرج#اكسبلور_تيك_توك #ترند #ترند_تيك_توك
1.2M viewsMay 28, 2024
TikTokawq_88
1:46
#طرب #لعب #رايح #رايح_بيشه #سامري #سامري_ثقيل #السعودية #بيشه #الرياض #الطائف #وادي_الدواسر #الافلاج #الخرج #اكسبلور_تيك_توك #ترند #ترند_تيك_توك
56.2K viewsJun 27, 2024
TikTokawq_88
0:27
Reasoning LLMs generate very long chains-of-thought, so even small quantization errors add up.With AWQ, Qwen3-4B drops 71.0 → 68.2 on MMLU-Pro (~4% relative loss). 😬ParoQuant fixes this! It keeps only the critical rotation pairs and fuses everything into a single kernel.Recovers most of the lost reasoning accuracy with minimal overhead — so 4-bit models stay strong at reasoning. 💪💪
169.1K views2 months ago
x.comZhijian Liu
See more
Static thumbnail place holder