#huggingface
3 articles
Latest
Tools
MiniMax M2.7 Quantized Models Enable Local Deployment
Unsloth and community developers release multiple GGUF quantizations of MiniMax M2.7, making the model viable for consumer hardware.
about 1 month ago3 min read
Tools
HuggingFace Cache Migration Breaks llama-server Workflows
Latest llama-server build automatically migrates local cache without warning, disrupting established workflows.
about 2 months ago2 min read
Tools
llama-server Breaking Change: HuggingFace Cache Migration Disrupts Workflows
Latest llama-server build auto-migrates local cache directories without user consent, sparking workflow friction.
about 2 months ago2 min read