Sovereign AI infrastructure.
Open models on-premises.
Talk to a 35B parameter model running on local hardware.
MODEL SPEC
ID: Qwen3.6-35B-A3B-MTP-UD-Q4_K_M.gguf
Parameters: 35.5 Billion
Quantization: 4-bit (Q4_K_M GGUF)
Context: 131,072 tokens
Engine: llama.cpp Server
0.70
UNLIMITED
0.95
0.00
ON-PREMISE INFERENCE ACTIVE
>