if you want to enable reasoning try compile llama.cpp with this quick Fix

then this will work ->

llama-server -m k2v2-Q4_K_M.gguf -ngl 99 -c 120000 --host 0.0.0.0 --port 8080 --jinja --chat-template-kwargs '{"reasoning_effort":"medium"}'

Downloads last month
1,028
GGUF
Model size
73B params
Architecture
llama
Hardware compatibility
Log In to view the estimation

2-bit

4-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for cturan/K2-V2-Instruct-GGUF

Base model

LLM360/K2-V2
Quantized
(7)
this model