---
language:
- pt
library_name: gguf
license: mit
license_link: https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B/blob/main/LICENSE
base_model: leandroxk/ornith-1.0-9b-kubeops
base_model_relation: quantized
pipeline_tag: text-generation
tags:
- gguf
- kubernetes
- devops
- kubeops
- troubleshooting
- incident-response
- tool-calling
- agentic
- qwen3.5
---

# Ornith-1.0-9B-KubeOps-GGUF 0.2.0

[English](./README.md)
·
[Português (Brasil)](./README.pt-BR.md)

[Transformers model](https://huggingface.co/leandroxk/ornith-1.0-9b-kubeops)
·
[GGUF quantizations](https://huggingface.co/leandroxk/ornith-1.0-9b-kubeops-GGUF)

GGUF quantizations of
[leandroxk/ornith-1.0-9b-kubeops](https://huggingface.co/leandroxk/ornith-1.0-9b-kubeops),
a Brazilian Portuguese fine-tune specialized in evidence-driven Kubernetes
incident diagnosis and safe, authorized recovery.

Version 0.2.0 adds a second, fully agentic operational fine-tuning stage. It
emphasizes deciding whether a change is necessary, identifying the actual
source of truth, executing the smallest authorized and reversible correction,
observing the resulting state, and validating the affected service end to end.

See the
[main model card](https://huggingface.co/leandroxk/ornith-1.0-9b-kubeops)
for training data, evaluation results, recommended uses, limitations, and
safety guidance.

## Files

| File | Quantization | Approximate size | Suggested use |
|---|---|---:|---|
| `ornith-1.0-9b-kubeops-f16.gguf` | F16 | 16.69 GiB | highest fidelity; requires more memory |
| `ornith-1.0-9b-kubeops-q8.gguf` | Q8_0 | 8.87 GiB | high fidelity with lower memory use than F16 |
| `ornith-1.0-9b-kubeops-q6_k.gguf` | Q6_K | 6.85 GiB | **recommended** balance of quality and memory use |
| `ornith-1.0-9b-kubeops-q4_k_m.gguf` | Q4_K_M | 5.24 GiB | lower memory use for constrained environments |

These sizes cover the model files only. Inference also requires memory for the
context, KV cache, and runtime overhead.

## Download

```bash
pip install -U "huggingface_hub"

hf download \
  leandroxk/ornith-1.0-9b-kubeops-GGUF \
  ornith-1.0-9b-kubeops-q6_k.gguf \
  --local-dir .
```

## llama.cpp usage

Use a recent version of
[llama.cpp](https://github.com/ggml-org/llama.cpp):

```bash
./llama-cli \
  -m ornith-1.0-9b-kubeops-q6_k.gguf \
  -cnv \
  -p "Investigate why the checkout Service has no Endpoints. Apply the minimum safe correction only if explicitly authorized."
```

To configure the context and GPU offload:

```bash
./llama-cli \
  -m ornith-1.0-9b-kubeops-q6_k.gguf \
  -cnv \
  -c 8192 \
  -ngl 99
```

The architecture declares a 262,144-token context window, but version 0.2.0 was
fine-tuned with sequences of up to 8,192 tokens. Very long contexts have not
been specifically evaluated for this model.

## Tool use

The source model can emit XML `<tool_call>` blocks. The 0.2.0 training dataset
used a generic `run_command` tool for diagnostic and corrective commands.

The host application must decide which commands are allowed, execute them,
return their results to the model, and enforce authorization. Use command
allowlists, execution and output limits, separate read-only and mutating
permissions, redact Secrets, and require explicit approval before every
mutation.

## Limitations and safety

GGUF conversion does not change the limitations of the source model. The model
may still invent identifiers, command output, causes, or successful recovery;
select the wrong source of truth; or suggest commands that are incompatible
with the cluster.

A successful command exit code is not proof of recovery. Observe the workload
after a change and separately validate the Service, EndpointSlice, route, or
affected application flow.

Quantization may reduce quality relative to the FP16 checkpoint. No comparative
benchmark has been completed across F16, Q8_0, Q6_K, and Q4_K_M for version
0.2.0.

## License

Distributed under the MIT license inherited from
[deepreinforce-ai/Ornith-1.0-9B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B).