Llamacpp

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

Patrick Hughes

May 13

GGUF Quantization Explained: Q4_K_M vs Q5_K_M vs Q8 — Which to Pick (2026)

#llamacpp #gguf #quantization #localai

4 min read

Aurora

May 13

Self-Hosted AI Agent Systems: Why Local Inference Matters More Than You Think

#rust #ai #llamacpp #selfhosted

4 min read

Simon Paxton

May 12

Discontinued Optane Local LLM Powers a Kimi K2.5 Desktop Run

#intel #optane #kimik25 #llamacpp

5 min read

Umair Bilal

Apr 26

Fixing Qwen 3.6 4090 llama.cpp Bug: 18 tok/s on My RTX 4090

#llm #llamacpp #rtx4090 #qwen

8 min read

Bruno Verachten

Apr 22

Running a 70B LLM on Pure RISC-V: The MilkV Pioneer Deployment Journey

#cpuinference #deepseekr1 #llamacpp #llm

17 min read

Bruno Verachten

Apr 22

First Words: LLM Inference on RISC-V

#bananapi #benchmark #inference #llamacpp

9 min read

Simon Paxton

Apr 19

Speculative Checkpointing Pays Off Only on Repetitive Text

#llamacpp #openai #nvidia #meta

7 min read

plasmon

Apr 14

llama.cppの設定で8GBの性能が5倍変わる — 主要オプションの最適値を出した

#llm #llamacpp #gpu

4 min read

plasmon

Apr 2

Parameter Count Is the Worst Way to Pick a Model on 8GB VRAM

#llm #locallm #gpu #llamacpp

5 min read

Simon Paxton

Mar 17

Unsloth Studio: The Open-Source LLM Studio To Try

#unslothstudio #llamacpp #googlecolab #lora

8 min read

Maksim Danilchenko

Apr 11

How to Run Gemma 4 Locally With Ollama, llama.cpp, and vLLM

#gemma4 #ollama #llamacpp #vllm

9 min read

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

DEV Community

# llamacpp

GGUF Quantization Explained: Q4_K_M vs Q5_K_M vs Q8 — Which to Pick (2026)

Self-Hosted AI Agent Systems: Why Local Inference Matters More Than You Think

Discontinued Optane Local LLM Powers a Kimi K2.5 Desktop Run

Fixing Qwen 3.6 4090 llama.cpp Bug: 18 tok/s on My RTX 4090

Running a 70B LLM on Pure RISC-V: The MilkV Pioneer Deployment Journey

First Words: LLM Inference on RISC-V

Speculative Checkpointing Pays Off Only on Repetitive Text

llama.cppの設定で8GBの性能が5倍変わる — 主要オプションの最適値を出した

Parameter Count Is the Worst Way to Pick a Model on 8GB VRAM

Unsloth Studio: The Open-Source LLM Studio To Try

How to Run Gemma 4 Locally With Ollama, llama.cpp, and vLLM