tobestyledintro/ Ternary-Bonsai-2-27B:27b-mmproj-bf16

1,661 yesterday

Mirror of Prism ML's Bonsai 2 27B ternary GGUF packs (PQ2_0 and PTQ1_0): a 27B hybrid-attention reasoning model in 6.70 GiB or 5.53 GiB, 262K context, vision and tool calling, Apache-2.0. Requires Prism ML's llama.cpp fork — stock Ollama cannot load

vision tools thinking 27b
... /
params
f6417cb1e269 · 42B
{
"temperature": 1,
"top_k": 20,
"top_p": 0.95
}