Видео с ютуба Low-Bit Quantization

The myth of 1-bit LLMs | Quantization-Aware Training

The myth of 1-bit LLMs | Quantization-Aware Training
Qwen3: Low-Bit Quantization & Performance

Qwen3: Low-Bit Quantization & Performance
1-Bit LLM: The Most Efficient LLM Possible?

1-Bit LLM: The Most Efficient LLM Possible?
ICQuant: Index Coding enables Low-bit LLM Quantization

ICQuant: Index Coding enables Low-bit LLM Quantization
OSDI '25 — DecDEC: Системный подход к развитию низкобитного квантования LLM

OSDI '25 — DecDEC: Системный подход к развитию низкобитного квантования LLM
Как LLM выживают в условиях низкой точности | Основы квантования

Как LLM выживают в условиях низкой точности | Основы квантования
Quantization in LLMs Explained Simply | How to Run Big AI Models on Small Hardware

Quantization in LLMs Explained Simply | How to Run Big AI Models on Small Hardware
Everything looks fine at 4-bit

Everything looks fine at 4-bit
INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats
Лекция 118: GSQ-RCO: Улучшенная неравномерная квантование GGUF

Лекция 118: GSQ-RCO: Улучшенная неравномерная квантование GGUF
Qwen3: Low-Bit Performance Study

Qwen3: Low-Bit Performance Study
Low-bit-width Large-model Quantization Challenge Live replay

Low-bit-width Large-model Quantization Challenge Live replay
GSQ-RCO: улучшенная неравномерная квантованная GGUF-модель

GSQ-RCO: улучшенная неравномерная квантованная GGUF-модель
LittleBit: ультранизкобитное квантование с помощью латентной факторизации

LittleBit: ультранизкобитное квантование с помощью латентной факторизации
Does 1-Bit Quantization Destroy LLM Logic?

Does 1-Bit Quantization Destroy LLM Logic?
Training models with only 4 bits | Fully-Quantized Training

Training models with only 4 bits | Fully-Quantized Training
How Effective Are Low bit Quantized LLaMA3 Models? An Empirical Analysis

How Effective Are Low bit Quantized LLaMA3 Models? An Empirical Analysis
tinyML Asia 2021 Dongsoo Lee: Extremely low-bit quantization for Transformers

tinyML Asia 2021 Dongsoo Lee: Extremely low-bit quantization for Transformers
How to Achieve Extreme Low-bit Quantization for LLMs

How to Achieve Extreme Low-bit Quantization for LLMs
How BitNet b1.58 Runs LLMs With Just 1.58-Bit Weights

How BitNet b1.58 Runs LLMs With Just 1.58-Bit Weights