Amaara Code 20B GGUF
early release of an agentic coding model
2 min readupdated
Amaara Code 20B is an SFT LoRA (a lightweight adapter layer on top of a base model) built for openai/gpt-oss-20b, which uses a Mixture-of-Experts (MoE, a multi-expert neural network) architecture. Trained on real-world agentic traces and coding tasks—primarily involving bash tool use—it outputs structured tool calls alongside dedicated channel markup (analysis, commentary, final). It is designed to run locally on consumer hardware in GGUF (a quantization format for efficient local LLM inference) and is well-suited for experimenting with AI agents.
Key features
- MoE base: 21B total parameters, with 3.6B active per token.
- Specialization: 82% of the training dataset consists of
bashtool calls. - Format: working round-1 GGUF export (the
Q4_K_Mfile is around 14.7 GB). - Limitations: no official benchmarks are available yet, as this is still an early preview build.
What you can do
- Run a local server: spin up the model with
llama-serverto test code generation and function calling. - Integrate into agent workflows: deploy it in environments that need a model trained to emit structured
bashcalls. - Inspect output channels: test how the model behaves across its custom channel tags (
analysis,commentary,final).
Example
llama-server -m amaara-code-20b-r1-Q4_K_M.gguf -ngl 99 -c 32768 --jinja \
--host 0.0.0.0 -ub 512 -b 1024Read more
Details• Training steps: 1,200 steps on a dataset of 98,391 agentic traces.
• Hardware requirements: at 14.7 GB, a 16 GB VRAM GPU requires partial offloading or a small context window.
• CPU speed: roughly 3.2 tokens per second on 48 threads.
• License: Apache-2.0.










Comments