clevis@tinyweights:/home$ cat ./welcome.txt
> Small language models like Gemma, Phi, SmolLM, and Qwen, run locally. Benchmarks, quantization, and hands-on deployment guides for small LLMs on real hardware. > New releases tested the week they drop. Straight talk on what is worth running and what is not. 46 posts · last updated 2026-07-19 · all writing CC BY 4.0
clevis@tinyweights:/home$ ls -lh --sort=time
06-01 7min guides Run ZAYA1-8B Locally: The 8B Reasoning MoE Trained on AMD 05-28 7min guides How to Run LFM2.5-1.2B-Thinking Locally: On-Device Reasoning Under 1GB 05-27 9min guides GGUF Quantization Levels Explained: Q4, Q5, Q8, and IQ Quants 05-27 6min guides How to Run Jamba Reasoning 3B Locally: AI21's Hybrid SSM-Transformer With a 256K Context 05-25 9min guides How to Run a Small LLM in Your Browser with WebLLM (No Install, No API) 05-25 6min guides How to Run Ministral 3 Locally: Mistral's 3B, 8B, and 14B Vision Models 05-24 7min news MedGemma 1.5: Google's 4B Medical Vision-Language Model You Can Run Locally 05-24 6min comparisons Qwen3.5-4B vs Phi-4-mini: Choosing the Right 4B Model for Local Inference 05-23 11min guides Running Local LLMs on Low-VRAM Windows GPUs (6GB and 8GB Cards) in 2026 05-21 10min guides What Can You Actually Do With a Local Small LLM? A Practical Guide