Quantization

Feeds to Scour
SubscribedAll
Scoured 47 posts in 4.8 ms

GGUF vs GPTQ vs AWQ: The Plain-English Guide to LLM Quantization (and Which One to Pick)

 ⚡ML Inference
vettedconsumer.com··Hacker News

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin

 🧠Deep Learning  Content type: Academic
arxiv.org·

Gemma 4 QAT on 10GB Laptop: Local AI with 6.7GB VRAM

 🦀WGPU
everylocalai.com··DEV

Linux 7.2 Preparing Intel Key Protection Technology "KPT" For Next-Gen QAT

 ⚙️Systems Programming
phoronix.com·

The latest Gemma 4 models use a training trick to slash their on-device memory footprint

 🖥️Systems ML
androidauthority.com·

Pruned YOLOv8 ONNX INT8 Fails: 3 Fixes That Work

 ⚡ML Inference  Content type: Blog  Content type: Discussion
tildalice.io·

Google Shrank Gemma 4 by 72% and Unsloth Fixed the 4-Bit Bug Nobody Else Caught on One 4090, and 4-Bit Shouldn’t Be This Good

 ⚡ML Inference  Content type: Blog
towardsai.net·

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

 ⚡ML Inference  Content type: News  Content type: Blog
blog.google··Hacker News

LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization

 🔄MLOps  Content type: Academic
arxiv.org·

Unsloth Gemma 4 QAT

 🎮GPU Programming
unsloth.ai·

Google DeepMind releases Gemma 4 QAT, but Unsloth developer Daniel Han warns naive llama.cpp conversions suffer accuracy loss

 ⚡ML Inference  Content type: News
digg.com·

google/gemma-4-12B-it-qat-q4_0-gguf

 ⚡ML Inference
huggingface.co·

Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression

 🖥️Systems ML  Content type: Academic
arxiv.org·

local llm on laptop 780M GPU using llama + gemma 4 qat

 🔄MLOps  Content type: Blog
alper.bearblog.dev·

Google releases Gemma 4 QAT models for local AI on enterprise laptops

 ⚡ML Inference
4sysops.com·

Quality Is Not a Safety Proxy Under Quantization

 🖥️Systems ML  Content type: Academic
arxiv.org·

Nvidia DGX Spark GB10 – AI Models and Guide with vLLM and Autonomous Script

 ⚡ML Inference  Content type: Code
github.com··Hacker News
Less-relevant results

MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent

 🎮GPU Programming  Content type: Blog
bric.pe.kr··DEV

Optimal Post-Training Quantization Scales and Where to Find Them

 🕸️Neural Networks  Content type: Academic
arxiv.org·

FMU Celebrates Distinguished Alumni | Francis Marion University

 🔗Distributed Training  Content type: Academic
fmarion.edu·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help