rjmalagon/granite3.2:8b-instruct-bf16

rjmalagon/

Bfloat16 version of the Granite3 dense 8B instruct model.

tools

12 Pulls Updated 5 weeks ago

Updated 5 weeks ago

5 weeks ago

127d69371a35 · 16GB

parameters8.17B

quantization(!unknown_file_type 32!)

{{- /* ------ MESSAGE PARSING ------ */}} {{- /* Declare the prompt structure variables to be fill

Apache License Version 2.0, January 2004

Readme

Bfloat16 version of the Granite3 dense 8B instruct model. Requires Ollama >v0.5.5 and BF16 supporting GPU (native or BF16 to FP32 on the fly llama.cpp conversion)

Full model info at https://ollama.com/library/granite3.2