Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
gpu
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Sizing a looped LLM: SenseNova-Loop-9B stores 32 layers, runs 56, and fits a 20 GB card
InferenceKey
InferenceKey
InferenceKey
Follow
for
InferenceKey
Nov 19
Sizing a looped LLM: SenseNova-Loop-9B stores 32 layers, runs 56, and fits a 20 GB card
#
ai
#
llm
#
gpu
#
selfhosted
Comments
Add Comment
4 min read
Moderation
How Much VRAM Does Your LLM Need? The Math Behind the EverXCloud Calculator
EverXCloud
EverXCloud
EverXCloud
Follow
Nov 19
How Much VRAM Does Your LLM Need? The Math Behind the EverXCloud Calculator
#
llm
#
gpu
#
machinelearning
#
opensource
Comments
Add Comment
4 min read
Moderation
How I Run a 27B Local Agent on a 12GB Laptop GPU: KVMem, Tiered KV, and Honest Long-Context Limits
Sparkle Qwen27b
Sparkle Qwen27b
Sparkle Qwen27b
Follow
Nov 19
How I Run a 27B Local Agent on a 12GB Laptop GPU: KVMem, Tiered KV, and Honest Long-Context Limits
#
llm
#
localai
#
gpu
#
opensource
Comments
Add Comment
6 min read
Moderation
FSDP vs DDP: when do you need sharded data parallel?
Viswaretas Kotra
Viswaretas Kotra
Viswaretas Kotra
Follow
Nov 19
FSDP vs DDP: when do you need sharded data parallel?
#
pytorch
#
machinelearning
#
deeplearning
#
gpu
Comments
Add Comment
9 min read
Moderation
DeepSeek V4.1 Flash at 42 tok/s with 256K Context on RTX 5070 Ti x2 + 5060 Ti — Full Benchmark Record
KeithVal
KeithVal
KeithVal
Follow
Nov 19
DeepSeek V4.1 Flash at 42 tok/s with 256K Context on RTX 5070 Ti x2 + 5060 Ti — Full Benchmark Record
#
llm
#
ai
#
gpu
#
machinelearning
Comments
Add Comment
10 min read
Moderation
LLM API vs. Dedicated Cloud GPU Break-Even Math in 2026 (Live Data)
stigla610
stigla610
stigla610
Follow
Nov 19
LLM API vs. Dedicated Cloud GPU Break-Even Math in 2026 (Live Data)
#
ai
#
llm
#
gpu
#
cloud
Comments
Add Comment
3 min read
Moderation
NVFP4 Won't Save Your VRAM: Quantization Tradeoffs on a 12GB Laptop GPU
Sparkle Qwen27b
Sparkle Qwen27b
Sparkle Qwen27b
Follow
Nov 19
NVFP4 Won't Save Your VRAM: Quantization Tradeoffs on a 12GB Laptop GPU
#
llm
#
localai
#
gpu
#
opensource
Comments
Add Comment
3 min read
Moderation
How do you estimate GPU hours and cost for a training run?
Viswaretas Kotra
Viswaretas Kotra
Viswaretas Kotra
Follow
Nov 19
How do you estimate GPU hours and cost for a training run?
#
machinelearning
#
ai
#
python
#
gpu
Comments
Add Comment
8 min read
Moderation
How much GPU memory does an LLM need? The whole sum, worked out on real cards
RONI DAS
RONI DAS
RONI DAS
Follow
Nov 19
How much GPU memory does an LLM need? The whole sum, worked out on real cards
#
llm
#
gpu
#
machinelearning
#
ai
Comments
Add Comment
9 min read
Moderation
کارت گرافیک دست دوم در ۲۰۲۶: چک لیست کامل قبل از خرید
Gaming IR
Gaming IR
Gaming IR
Follow
Nov 19
کارت گرافیک دست دوم در ۲۰۲۶: چک لیست کامل قبل از خرید
#
gaming
#
hardware
#
pcgaming
#
gpu
Comments
Add Comment
1 min read
Moderation
Скачал полтерабайта локальных LLM — но без GPU жизни нет
Alexey Bolshakov
Alexey Bolshakov
Alexey Bolshakov
Follow
Nov 19
Скачал полтерабайта локальных LLM — но без GPU жизни нет
#
ai
#
localai
#
gpu
#
agents
Comments
Add Comment
12 min read
Moderation
When does reserved GPU capacity beat on-demand pricing?
Viswaretas Kotra
Viswaretas Kotra
Viswaretas Kotra
Follow
Nov 19
When does reserved GPU capacity beat on-demand pricing?
#
gpu
#
cloud
#
aws
#
machinelearning
Comments
Add Comment
9 min read
Moderation
How many tokens per second should an LLM serve on one GPU?
Viswaretas Kotra
Viswaretas Kotra
Viswaretas Kotra
Follow
Nov 18
How many tokens per second should an LLM serve on one GPU?
#
llm
#
machinelearning
#
gpu
#
performance
Comments
Add Comment
8 min read
Moderation
What are the best Shadeform alternatives for buying GPU time?
Viswaretas Kotra
Viswaretas Kotra
Viswaretas Kotra
Follow
Nov 18
What are the best Shadeform alternatives for buying GPU time?
#
gpu
#
cloud
#
machinelearning
#
ai
Comments
Add Comment
9 min read
Moderation
Why can a multi-GPU job wait while GPUs are idle?
Denis Voronko
Denis Voronko
Denis Voronko
Follow
for
Nodeox
Nov 18
Why can a multi-GPU job wait while GPUs are idle?
#
machinelearning
#
ai
#
hpc
#
gpu
Comments
Add Comment
4 min read
Moderation
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account