#gguf
Gguf: 8 AI articles covering gguf news, analysis, and research
Articles
Nace AI Open-Sources Drex Max v1: A 27B Decision Model That Runs⭐9
Nace AI open-sources Drex Max v1, a 27B decision model with 262K context that runs locally on Apple Silicon and NVIDIA GPUs via GGUF and llama.cpp forks.
Liquid AI Releases LFM3: Six Open-Weight 2B-Class Multimodal⭐8
Liquid AI's LFM3 offers six open-weight 2B-class multimodal models on one shared backbone, running on phones and laptops at ~1GB memory with 256K context.
Running Underdog Saluki 27B: A 2-Bit Qwen3.8-27B Tool-Calling Guide⭐9
A hands-on guide to Underdog Saluki 27B, a 7.9 GB 2-bit Qwen3-27B build. We diff its GGUF, serve it in llama.cpp, and score tool calling on 120 BFCL tasks.
Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE Built for On⭐8
Liquid AI releases LFM2.5-24B-A2B, a 24B MoE with 2B active parameters built for on-device agents, delivering fast local tool calling on laptops and PCs.
Nace AI Open-Sources Drex 1.5: A 9B Decision Model That Scores⭐8
Nace AI open-sourced Drex 1.5, a 9B decision model for agents that scores options instead of generating text. It tops the Decision Index under 10B parameters.
Hugging Face Transformers Now Runs llama.cpp Quants Natively⭐8
Hugging Face Transformers now natively supports llama.cpp GGUF quantized models, letting you run efficient local LLMs and multimodal models directly via the Tra...
GGUF vs GPTQ vs AWQ vs EXL2: LLM Model Formats Explained (2026)⭐10
GGUF vs GPTQ vs AWQ vs EXL2 explained for 2026: compare LLM model formats, containers, and quantization methods to choose the right one for deployment.
PrismML Releases Ternary Bonsai 2 27B: A 5.9 GB Apache 2.0 Model⭐8
PrismML's Ternary Bonsai 2 27B packs Qwen3.8 27B into 5.9 GB under Apache 2.0, keeping 98.2% of benchmark performance with 262K context and image support.