Llama
nanollama: Train Your Own Llama 3 From Scratch on Custom Data
Pretrain Llama 3 architecture models from raw text, export to GGUF, and run with llama.cpp. Forked from Karpathy's nanochat. 46M to 7B parameters.
Qwen vs Llama vs Mistral: Which Model Family Should You Build On?
Qwen has 201 languages and a model for every task. Llama has the biggest community. Mistral pioneered efficient MoE. Decision framework for choosing your model family in 2026.
Running 70B Models Locally — Exact VRAM by Quantization
Llama 3.3 70B needs 43GB at Q4, 75GB at Q8, 141GB at FP16. Every quant level, which GPUs fit, real speeds, and when a 27B or MoE model is the smarter buy.
Local LLMs vs Claude: When Each Actually Wins
Qwen 3 32B matches Claude on daily tasks at zero marginal cost. Claude still wins on 200K-token documents and multi-step debugging. Benchmarks, pricing, and when to use each.