llama.cpp GGUF
llama.cpp GGUF Articles
Browse 3 articles about llama.cpp GGUF.
Underdog Saluki 27B: Tool Calling Gains vs Full-Size Qwen3.8 Losses
Underdog Saluki 27B compresses Qwen3.8-27B to under 8GB. Here's where it beats the full model on tool calling and where it falls short.
Underdog Saluki benchmarksBFCL tool callingQwen3.8-27B comparison
Run Underdog Saluki 27B Locally with Llama.cpp: Full Setup Guide
Download, configure, and serve Underdog Saluki 27B, a sub-8GB Qwen3.8-27B GGUF quant, with llama.cpp and tool calling intact.
Underdog Saluki 27Brun Qwen3.8 locallyllama.cpp GGUF
MiniCPM5-2B GGUF: How Does It Hold Up Locally?
Hands-on test of MiniCPM5-2B GGUF quantization with llama.cpp, checking reasoning, coding, and multilingual accuracy versus full precision.
MiniCPM5-2B GGUFMiniCPM5 quantizedrun MiniCPM5 locally