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
GPU Memory
🎮 GPU Memory
GPU memory hierarchy, unified memory, CUDA memory
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
301
posts in
15.1
ms
Gemma 4 QAT on 10GB Laptop: Local AI with 6.7GB
VRAM
🔌
IOMMU
everylocalai.com
·
42m
42 minutes ago
·
DEV
Actions for Gemma 4 QAT on 10GB Laptop: Local AI with 6.7GB VRAM
Nvidia RTX Spark Unreal Engine: GB10 Blackwell Laptop with 128GB
Unified
Memory
🔷
SPIR-V
armdevices.net
·
6d
6 days ago
Actions for Nvidia RTX Spark Unreal Engine: GB10 Blackwell Laptop with 128GB Unified Memory
SK Hynix bets
HBM
, wins Nvidia jackpot
🎮
GPU Scheduling
jonpeddie.com
·
1d
1 day ago
Actions for SK Hynix bets HBM, wins Nvidia jackpot
Massive AI Storage Demand Creates a New
Memory
Wall
⚡
CPU Caches
Content type:
News
eetimes.com
·
6h
6 hours ago
Actions for Massive AI Storage Demand Creates a New Memory Wall
Enhancing High Bandwidth
Memory
(
HBM
) Reliability With 3D X-ray Inspection
🔌
PCIe
semiengineering.com
·
1d
1 day ago
Actions for Enhancing High Bandwidth Memory (HBM) Reliability With 3D X-ray Inspection
AMD Believes
Unified
Memory
Architectures Open Up a "World of Possibilities", Will Shape Their Product Choices & Roadmaps In Future
🔗
IPC
Content type:
News
wccftech.com
·
3d
3 days ago
Actions for AMD Believes Unified Memory Architectures Open Up a "World of Possibilities", Will Shape Their Product Choices & Roadmaps In Future
NVIDIA chip powers local AI workloads
🎮
GPU Scheduling
edn.com
·
2h
2 hours ago
Actions for NVIDIA chip powers local AI workloads
2x GH200 for LLM inference, Part 2: vLLM, DeepSeek V4 Flash, and MTP
⚙️
Kernel Dev
Content type:
Blog
dnhkng.github.io
·
2d
2 days ago
Actions for 2x GH200 for LLM inference, Part 2: vLLM, DeepSeek V4 Flash, and MTP
KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4
GPU
(gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.
🎮
GPU Scheduling
Content type:
Code
github.com
·
5h
5 hours ago
·
Hacker News
Actions for KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.
GGUF vs GPTQ vs AWQ: The Plain-English Guide to LLM Quantization (and Which One to Pick)
🗜️
Compression Algorithms
vettedconsumer.com
·
4d
4 days ago
·
Hacker News
Actions for GGUF vs GPTQ vs AWQ: The Plain-English Guide to LLM Quantization (and Which One to Pick)
Tech leaker claims that the RTX 50 Super refresh is still on, despite the RAMpocalypse, and it'll be joined by a 12 GB RTX 5060
🔌
PCIe
Content type:
News
pcgamer.com
·
1d
1 day ago
Actions for Tech leaker claims that the RTX 50 Super refresh is still on, despite the RAMpocalypse, and it'll be joined by a 12 GB RTX 5060
Nvidia RTX Spark: The $2,900 Floor Tells You Everything
🎮
GPU Scheduling
Content type:
Blog
Content type:
Discussion
tildalice.io
·
6d
6 days ago
Actions for Nvidia RTX Spark: The $2,900 Floor Tells You Everything
High Bandwidth Flash | A New
Memory
for AI Data Centers and Edge Computing | Sandisk
✍️
Write Amplification
ncnonline.net
·
1d
1 day ago
Actions for High Bandwidth Flash | A New Memory for AI Data Centers and Edge Computing | Sandisk
GMKtec EVO-X3 mini PC is coming with OCuLink support and a Ryzen AI MAX+ PRO 495 variant packing 192GB of
memory
🔌
PCIe
Content type:
News
tweaktown.com
·
2d
2 days ago
Actions for GMKtec EVO-X3 mini PC is coming with OCuLink support and a Ryzen AI MAX+ PRO 495 variant packing 192GB of memory
Re
: Things that made you go "WTF?" today o_O
🔄
Memory Reclaim
bay12forums.com
·
5d
5 days ago
Actions for Re: Things that made you go "WTF?" today o_O
Nvidia GeForce RTX 50 Super GPUs may launch in early 2027 with 50% more
VRAM
🎮
GPU Scheduling
club386.com
·
1d
1 day ago
Actions for Nvidia GeForce RTX 50 Super GPUs may launch in early 2027 with 50% more VRAM
NVIDIA's RTX 5060 May Finally Get The
VRAM
Upgrade Gamers Wanted
🎮
GPU Scheduling
Content type:
News
hothardware.com
·
5d
5 days ago
Actions for NVIDIA's RTX 5060 May Finally Get The VRAM Upgrade Gamers Wanted
Apple's most advanced on-device AI features will only work on select devices
⚡
Storage Class Memory
Content type:
News
gsmarena.com
·
1d
1 day ago
Actions for Apple's most advanced on-device AI features will only work on select devices
From
GPU
to Token: The 8-Layer Observability Stack for AI Infrastructure
🎮
GPU Scheduling
Content type:
Blog
jimmysong.io
·
1d
1 day ago
Actions for From GPU to Token: The 8-Layer Observability Stack for AI Infrastructure
Running Qwen 35B MoE at 450k Context on a Single 32GB
GPU
🔗
IPC
local-llm.utop.workers.dev
·
3d
3 days ago
·
Hacker News
Actions for Running Qwen 35B MoE at 450k Context on a Single 32GB GPU
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