theOG-50M
DrunkkToys · Kit
Writes a Python function from a plain English request. A 50M parameter code model trained from scratch on one laptop, small enough to run offline in Ollama, LM…
New
AI projects from Hugging Face
Categories and filters
Listings
Maximizing Model Performance Guide
DavidAU · Kit
Guides you in tuning samplers and parameters for local language models, with steps for system prompts, reasoning models and expert settings in LM Studio, Silly…
New
Qwen3.8-27B-GGUF by lmstudio-community
lmstudio-community · Kit
A GGUF quantization of Qwen's Qwen3.8-27B made by the LM Studio team with llama.cpp, for people who run a 27B model on their own computer.
New