Skip to content

winnow

3 TagsUpdated Apache-2.0by EldanRing

Decision models by EldanRing, fine-tuned from Google's Gemma 4 and published as GGUF. Winnow reads the answer labels' logits after its own prompt; Ollaya runs the author's file on llama.cpp, on NVIDIA GPUs, Apple silicon or the CPU.

decisionmultilingualfine-tunedgguf7.5b12b

Tags

Name
winnowlatestSame as winnow:12b.12.7 GB · 8192 ctx · 100+ languages
winnow:12bWinnow-12B, Q8_0 GGUF: 0.702 on typed decisions, 85.7 % on the author's JevBench set; a 16 GB GPU holds it.12.7 GB · 8192 ctx · 100+ languages
winnow:e4bWinnow-E4B, Q8_0 GGUF, with the author's fitted temperature: 0.722 on typed decisions, smaller and faster than 12b.8.0 GB · 8192 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.