Skip to content

cygnet

2 TagsUpdated Apache-2.0by blockbrain-ai

Frozen Gemma 4 12B IT with blockbrain-ai's Cygnet prompt: the options as letters, one answer slot, and one calibration temperature. No fine-tuning; Ollaya runs ggml-org's Q8_0 GGUF on llama.cpp.

decisionmultilingualgguf12b

Tags

Name
cygnetlatestSame as cygnet:12b.12.7 GB · 16384 ctx · 100+ languages
cygnet:12bGemma 4 12B IT (Q8_0) with Cygnet's prompt and temperature 3.4: 0.683 on typed decisions, up to 20 options.12.7 GB · 16384 ctx · 100+ languages

Tags without a suffix load fp16 on a CUDA GPU and fp32 on CPU; add -fp16 or -fp32 to pin one precision.