How to use from
Lemonade
Pull the model
# Download Lemonade from https://lemonade-server.ai/
lemonade pull OpenAdminOS/openadmin-20b-GGUF:MXFP4
Run and chat with the model
lemonade run user.openadmin-20b-GGUF-MXFP4
List all available models
lemonade list
Quick Links

OpenAdmin 20B β€” GGUF

GGUF quantizations of OpenAdmin 20B for llama.cpp, Ollama, LM Studio, and OpenAdminOS.

File Quant Size Notes
openadmin-20b-MXFP4.gguf MXFP4 (MoE) ~12 GB native gpt-oss format; runs on 16 GB machines

Uses the standard gpt-oss harmony chat template embedded in the file; no custom template required.

Downloads last month
13
GGUF
Model size
21B params
Architecture
gpt-oss
Hardware compatibility
Log In to add your hardware

4-bit

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

Model tree for OpenAdminOS/openadmin-20b-GGUF

Quantized
(1)
this model