LocalLLaMA !localllama@sh.itjust.works

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

---

Read more

Members

3,367

Posts

351

Active Today

29

Created

2 yr. ago

Moderators

---

How to install Ollama on Arch Linux

Llama 3.1 Community License is not a free software license

EXAONE Deep ━ Setting a New Standard for Reasoning AI - LG AI Research News

Mistral small 3.1 released

Returning back to where it started with llama 3 8B. DeepHermes is a great for 8gb VRAM cards

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching

Recommendations for a lightweight Python LLM framework for a webapp?

Loaded benchmark for 1-3-4-7b models?

Can Your LLM pass the Sun Theft Vibe Check (STVC) benchmark?

DeepHermes Preview features swappable standard output to R1 distill CoT reasoning. Its kind of blowing my mind.

Gemma 3 1B and 3B result on a "needle in a haystack" like test ran locally

New release: Gemma 3 family of models

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

NVIDIA's GeForce RTX 4090 With 96GB VRAM Reportedly Exists; The GPU May Enter Mass Production Soon, Targeting AI Workloads

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