#gemma

📰

Size Your Model to Where You Run It: Gemma 4 E2B and E4B on an AWS L4 and Two Small GPUs

DEV Community: aws·xbill·about 5 hours ago

A 24 GB NVIDIA L4 serves Gemma 4 E2B and E4B at only 1.2-1.3x an 8 GB desktop RTX 3050 for one user, with the same answers, because a 4-bit small model uses 13-29% of the card. Pick the model for the hardware, and the hardware for the model.

15s

📰

0Read More

Size Your Model to Where You Run It: Gemma 4 E2B and E4B on an AWS L4 and Two Small GPUs

DEV Community: aws·xbill·about 5 hours ago

#fi4BiesS

#devtoaws #devto #dev #drafter #card

A 24 GB NVIDIA L4 serves Gemma 4 E2B and E4B at only 1.2-1.3x an 8 GB desktop RTX 3050 for one user, with the same answers, because a 4-bit small model uses 13-29% of the card. Pick the model for the hardware, and the hardware for the model.

15s

Uncensored AI models 2026: October’s builds, priced

📰

0Read More

Uncensored AI models 2026: October’s builds, priced

DEV Community: api·UplinkSwitch·about 17 hours ago

#yBq3Abfs

#devtoapi #devto #dev #uncensored #steady

A dated log of every uncensored, abliterated and roleplay build that joined the catalog in October 2026, by the day it went on sale: what each is, 100 mess…

15s

LLM Research Blog: The Model That Fits My Kinyarwanda-to-English Translation Project

📰

0Read More

LLM Research Blog: The Model That Fits My Kinyarwanda-to-English Translation Project

DEV Community: nlp·Tuyishimire claudine·about 24 hours ago

#u0a33axz

#devtonlp #devto #dev #model #gemma

Introduction During our Natural Language Processing (NLP) studies, I developed a...

15s

A 14.4 GB model on a 16 GB Mac: keep the right experts, not all of them

📰

0Read More

A 14.4 GB model on a 16 GB Mac: keep the right experts, not all of them

DEV Community: typescript·Vin Joseph·1 day ago

#2x7nuV2J

#devtotypescript #devto #dev #model #experts

A 16 GB Mac mini gives its GPU about 12.7 GB. Google's Gemma 4 26B-A4B, in its official 4-bit file,...

15s

Sloth Archivist: Clean Your Camera Roll and Journal As You Sleep

📰

0Read More

Sloth Archivist: Clean Your Camera Roll and Journal As You Sleep

DEV Community: opensource·S.Busienei·1 day ago

#qCkqIfKo

#devtoopensource #devto #dev #model #every

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

15s

Four Birthdays, Two Family Dinners, and One Extremely Expensive December

🖼️

0Read More

Four Birthdays, Two Family Dinners, and One Extremely Expensive December

DEV Community: opensource·AsiMir·1 day ago

#fGe8txrR

#devtoopensource #devto #dev #tabpfn #gemma

A lazy Telegram bot reads my receipts with Gemma and sees Wall Day coming with TabPFN.

15s

Do It or Dodge It: a Gemma on my phone either shrinks the task or writes the excuse

📰

0Read More

Do It or Dodge It: a Gemma on my phone either shrinks the task or writes the excuse

DEV Community: flutter·Chestly Ace·1 day ago

#g2SUTyA9

#devtoflutter #devto #dev #model #dodge

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

15s

🖼️

0Read More

Too lazy to read my newsletters, so I built an AI that reads them to me

DEV Community: ai·Victory Lucky·1 day ago

#FVMLLfUd

#devtoai #devto #dev #episode #worker

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady My inbox...

15s

7.5% Cashback Isn’t a Price. I Built TripStack to Read the Rest.

🖼️

0Read More

7.5% Cashback Isn’t a Price. I Built TripStack to Read the Rest.

DEV Community: python·JIAYI YIN·2 days ago

#5HrrKl2G

#devtopython #devto #dev #model #gemma

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. ...

15s

EOD Report: my daily status report to the CEO, drafted by a local Gemma 4

📰

0Read More

EOD Report: my daily status report to the CEO, drafted by a local Gemma 4

DEV Community: productivity·adi-ray·2 days ago

#dppByyK9

#devtoproductivity #devto #dev #task #every

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

15s

Running Modern SLMs (Gemma 4, Qwen 3 & Phi-4) on CPU: Pure Rust, Zero Python

📰

0Read More

Running Modern SLMs (Gemma 4, Qwen 3 & Phi-4) on CPU: Pure Rust, Zero Python

DEV Community: rust·Hossein Mortazavi·2 days ago

#VuKIVEoF

#devtorust #devto #dev #model #gemma

Beyond Python: Benchmarking Modern SLMs (Gemma 4, Qwen 3 & Phi-4) on CPU with Pure Rust...

15s

SnapCode 🦥: I stopped retyping code from lecture slides. One hotkey, offline, Gemma does the rest

🖼️

0Read More

SnapCode 🦥: I stopped retyping code from lecture slides. One hotkey, offline, Gemma does the rest

DEV Community: opensource·Sachindu Nethmin·3 days ago

#nT3MfVaa

#devtoopensource #devto #dev #snapcode #code

This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 3 What I...

15s

I tried turning my old Samsung Galaxy into a local LLM-hosting machine, and it worked better than I expected

🖼️

0Read More

I tried turning my old Samsung Galaxy into a local LLM-hosting machine, and it worked better than I expected

XDA ·Shekhar Vaidya·3 days ago

#5r1sVAeK

#xdadevelopers #xda-developers #gemma #model #termux

View the full article

Create a free account to read full articles inline — no redirect to the original site.

Create account Log in

Mumble: say it now, and open models sort it out at 3 AM while you sleep 🦥

🖼️

0Read More

Mumble: say it now, and open models sort it out at 3 AM while you sleep 🦥

DEV Community: ai·Kourtney Lee·3 days ago

#jt2nwYmA

#devtoai #devto #dev #memos #memo

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

15s

My local models are worse than Claude at almost everything, but they still run most of my workflow for $0

🖼️

0Read More

My local models are worse than Claude at almost everything, but they still run most of my workflow for $0

XDA ·Abhinav Raj·4 days ago

#7YJxGscG

#xdadevelopers #xda-developers #claude #model #models

View the full article

Create a free account to read full articles inline — no redirect to the original site.

Create account Log in

lazy-ledger: a bank statement turns into a one-page money report, offline, with Gemma

🖼️

0Read More

lazy-ledger: a bank statement turns into a one-page money report, offline, with Gemma

DEV Community: opensource·Sergei Berets·4 days ago

#g0aBef1S

#devtoopensource #devto #dev #gemma #month

This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 3. What I...

15s

My phone counts every reel I watch, and a 1.9 GB Gemma judges me for it

🖼️

0Read More

My phone counts every reel I watch, and a 1.9 GB Gemma judges me for it

DEV Community: android·Jayant Jeet Tomar·6 days ago

#h99Fvlob

#devtoandroid #devto #dev #open #phone

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

15s

Sift: share it, sleep, it's filed — on-device Gemma, no cloud

🖼️

0Read More

Sift: share it, sleep, it's filed — on-device Gemma, no cloud

DEV Community: android·Fahad Irshad·6 days ago

#NT6j0Ajd

#devtoandroid #devto #dev #model #file

A junk drawer that files itself: two taps to keep anything, then an on-device Gemma sorts it overnight. No internet permission, no accounts, no cloud.

15s

Fine-Tuning Gemma 4 with QLoRA for Customer Support - PyImageSearch

🖼️

0Read More

Fine-Tuning Gemma 4 with QLoRA for Customer Support - PyImageSearch

PyImageSearch·Piyush Thakur·6 days ago

#aXeJR6Lp

#pyimagesearch #model #fine #gemma #support

Fine-tune Gemma 4 with QLoRA on the Bitext dataset to build a memory-efficient customer support model using LoRA adapters and TRL.

15s

Menu

Size Your Model to Where You Run It: Gemma 4 E2B and E4B on an AWS L4 and Two Small GPUs

Size Your Model to Where You Run It: Gemma 4 E2B and E4B on an AWS L4 and Two Small GPUs

Uncensored AI models 2026: October’s builds, priced

LLM Research Blog: The Model That Fits My Kinyarwanda-to-English Translation Project

A 14.4 GB model on a 16 GB Mac: keep the right experts, not all of them

Sloth Archivist: Clean Your Camera Roll and Journal As You Sleep

Four Birthdays, Two Family Dinners, and One Extremely Expensive December

Do It or Dodge It: a Gemma on my phone either shrinks the task or writes the excuse

Too lazy to read my newsletters, so I built an AI that reads them to me

7.5% Cashback Isn’t a Price. I Built TripStack to Read the Rest.

EOD Report: my daily status report to the CEO, drafted by a local Gemma 4

Running Modern SLMs (Gemma 4, Qwen 3 & Phi-4) on CPU: Pure Rust, Zero Python

SnapCode 🦥: I stopped retyping code from lecture slides. One hotkey, offline, Gemma does the rest

I tried turning my old Samsung Galaxy into a local LLM-hosting machine, and it worked better than I expected

Mumble: say it now, and open models sort it out at 3 AM while you sleep 🦥

My local models are worse than Claude at almost everything, but they still run most of my workflow for $0

lazy-ledger: a bank statement turns into a one-page money report, offline, with Gemma

My phone counts every reel I watch, and a 1.9 GB Gemma judges me for it

Sift: share it, sleep, it's filed — on-device Gemma, no cloud

Fine-Tuning Gemma 4 with QLoRA for Customer Support - PyImageSearch