LocalLLaMA !localllama@sh.itjust.works

Welcome to LocalLLaMA! Here we discuss running and developing machine learn

---

Read more

Members

3,576

Posts

328

Active Today

5

Created

2 yr. ago

Moderators

---

Is there a German 7B Vision Model?

Sorting-Free GPU Kernels for LLM Sampling

Reka Flash, open source 21B model comparable to QWQ 32B

Qwen/QwQ-32B · Hugging Face

Mac Studio 2025

Chain of Draft: Thinking Faster by Writing Less

Atom of Thoughts (AOT): lifts gpt-4o-mini to 80.6% F1 on HotpotQA, surpassing o3-mini and DeepSeek-R1

Apparently microsofts new phi-4-mini is business-tuned?

Framework just announced their new Desktop: an AI powerhorse?

Anyone found "optimal" settings for llama.cpp partial offload?

Psychoanalysis

AMD CPU, Apple M4 Pro Performance - Ryzen AI MAX Review

Trying out old GPUs with Vulkan

Models not loading into RAM

AMD denies rumors of Radeon RX 9070 XT with 32GB memory

Recommend models for GTX 1660 Super (6GB)

How to run LLaMA (and other LLMs) on Android.

What is a good model that runs on 6GB Vram?

unsure on how to quantize model

Go toolchain error - Does anyone know what's going on here?