Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
llm
🤖 llm
Specific
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
1975
posts in
9.8
ms
Unsloth
Gemma
4 QAT
🔄
Transformer Models
unsloth.ai
·
5d
5 days ago
Actions for Unsloth Gemma 4 QAT
Ollama
0.30 GPU Boost: Faster local
Qwen
inference
on NVIDIA
🗄️
Vector Databases
everylocalai.com
·
17h
17 hours ago
·
DEV
Actions for Ollama 0.30 GPU Boost: Faster local Qwen inference on NVIDIA
defai-digital/ax-engine
: Apple Silicon
LLM
runtime supporting
Gemma
4 and Qwen 3.6 MTP modes
🔄
Transformer Models
Content type:
Code
github.com
·
1d
1 day ago
·
Hacker News
Actions for defai-digital/ax-engine: Apple Silicon LLM runtime supporting Gemma 4 and Qwen 3.6 MTP modes
Fine-tuning
Multi-modal LLMs with ART: Art-based Reinforcement Training
🔄
Transformer Models
Content type:
Academic
arxiv.org
·
9h
9 hours ago
Actions for Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training
Google fills out the middle with the
Gemma
4 12B
🤖
AI coding
jonpeddie.com
·
1d
1 day ago
Actions for Google fills out the middle with the Gemma 4 12B
Gemma
4 QAT
models
: Optimizing model compression for mobile and laptop efficiency
🔄
Transformer Models
Content type:
News
Content type:
Blog
blog.google
·
5d
5 days ago
·
Hacker News
Actions for Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency
Intelligent
inference
scheduling with
llm-d
on Red Hat AI
🔄
Transformer Models
developers.redhat.com
·
13h
13 hours ago
Actions for Intelligent inference scheduling with llm-d on Red Hat AI
MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent
🔄
Transformer Models
Content type:
Blog
bric.pe.kr
·
2d
2 days ago
·
DEV
Actions for MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent
Google unveils DiffusionGemma, delivering up to 4x faster
inference
on dedicated GPUs
🗄️
Vector Databases
alternativeto.net
·
1h
1 hour ago
Actions for Google unveils DiffusionGemma, delivering up to 4x faster inference on dedicated GPUs
NVIDIA Accelerates Google DeepMind’s DiffusionGemma for Local AI
🔄
Transformer Models
Content type:
Blog
blogs.nvidia.com
·
21h
21 hours ago
Actions for NVIDIA Accelerates Google DeepMind’s DiffusionGemma for Local AI
google/gemma-4-12B-it-qat-q4
_0-gguf
🔄
Transformer Models
huggingface.co
·
5d
5 days ago
Actions for google/gemma-4-12B-it-qat-q4_0-gguf
DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200
🔄
Transformer Models
Content type:
News
newsletter.semianalysis.com
·
2d
2 days ago
·
Hacker News
Actions for DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200
What
Ollama
Reveals About Local AI, Agents, and Open
Models
🤖
AI coding
Content type:
Blog
odsc.medium.com
·
15h
15 hours ago
Actions for What Ollama Reveals About Local AI, Agents, and Open Models
Inferoa
AI harness claimed 90% cache savings. We ran it and measured 97.8%
🤖
AI coding
zozo123.github.io
·
1d
1 day ago
·
Hacker News
Actions for Inferoa AI harness claimed 90% cache savings. We ran it and measured 97.8%
Running
LLM
Inference
on Kubernetes: What It Actually Takes
🔄
Transformer Models
Content type:
Blog
fairwinds.com
·
5d
5 days ago
Actions for Running LLM Inference on Kubernetes: What It Actually Takes
Google’s DiffusionGemma is 4x faster than its other
Gemma
models
🔄
Transformer Models
thenewstack.io
·
20h
20 hours ago
Actions for Google’s DiffusionGemma is 4x faster than its other Gemma models
New comment by alroma90 in "Ask HN: Who wants to be hired? (June 2026)"
🔍
RAG
Content type:
Discussion
news.ycombinator.com
·
3h
3 hours ago
·
Hacker News
Actions for New comment by alroma90 in "Ask HN: Who wants to be hired? (June 2026)"
lightmetal: GPU
LLM
Inference
From a Single Java 25 JAR
🔄
Transformer Models
Content type:
Blog
adambien.blog
·
2d
2 days ago
Actions for lightmetal: GPU LLM Inference From a Single Java 25 JAR
The latest
Gemma
4
models
use a training trick to slash their on-device memory footprint
🔄
Transformer Models
androidauthority.com
·
5d
5 days ago
Actions for The latest Gemma 4 models use a training trick to slash their on-device memory footprint
How
Gemma
Collins’ dad saved her from
financial
ruin & helped rake in £1.4M last year… he even lives with her & fiancé
🔍
RAG
Content type:
News
thesun.co.uk
·
2d
2 days ago
Actions for How Gemma Collins’ dad saved her from financial ruin & helped rake in £1.4M last year… he even lives with her & fiancé
Page 2 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
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
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help