Llamacpp - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

xbill for Google Developer Experts

Oct 2

Gemma 4 at Over 70 Tokens/s on a 2021 Laptop's 4 GB GPU: The Live Demo, Step by Step

#gemma #llamacpp #cuda #huggingface

12 min read

Dmitry Amelchenko

Oct 3

Inside My llama.cpp Setup: Tuning Qwen 3.8 27B for 512K Context

#ai #llm #localllm #llamacpp

7 min read

pielouNW

Oct 1

When Chat Templates Go Wrong

#llm #opensource #ai #llamacpp

7 min read

Rost

Sep 14

llama.cpp vs Ollama in 2026: Which Runtime Should You Run?

#llamacpp #ollama #llm #selfhosting

18 min read

xbill for Google Developer Experts

Sep 23

A 4 GB Laptop GPU vs a 6-Core CPU on Gemma 4, Re-Measured in ABBA Order: 4.1x

#gemma #llamacpp #cuda #benchmarking

11 min read

Rost

Sep 12

ROCm vs Vulkan for AMD Local LLM Hosting: 2026 Guide

#llm #selfhosting #llamacpp #ollama

20 min read

Rost

Sep 11

KV Cache on 16 GB GPUs: Making Long Context Actually Fit

#llm #llamacpp #vllm #ollama

22 min read

Donald Lee

Sep 29

How to pick --n-cpu-moe in llama.cpp: Qwen3.6 35B-A3B on 12, 16 and 24 GB GPUs

#llm #llamacpp #localai #gpu

3 min read

Vishnu Hari Dadhich

Sep 7

Running llama.cpp on a 32 GB MacBook Air: A Direct Comparison with Ollama

#ai #localllm #llamacpp #ollama

9 min read

Aug 23

Fix Local LLM Quality: Context Stacking & Rope Freq Tweaks

#localllms #aiagents #ollama #llamacpp

8 min read

Shaam

Sep 25

Ollama vs LM Studio 2026: Ollama Wins for Devs

#ollama #lmstudio #localllm #llamacpp

7 min read

Jasur Yuldoshev

Aug 21

"V cache quantization requires flash_attn" — the llama.cpp error that quietly halves your context window

#llamacpp #llm #performance #debugging

10 min read

Sep 18

How to Run GGUF Models Locally: Ollama, llama.cpp & vLLM

#ai #gguf #ollama #llamacpp

5 min read

Sep 18

llama.cpp vs Ollama: Which Should You Run in 2026?

#ai #llamacpp #ollama #localllm

6 min read

Aug 11

Nine ways to talk to a local model

#localllm #ollama #llamacpp #buildinpublic

9 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.