Downloads · 30 days
0
eumel8/ornith-k8s
ornith-k8s is a text generation model from eumel8. Use it when you need the model to write or continue text. The card lists the license as mit.
ORNITH-K8S — LOCAL DEVOPS AGENT FOR KUBERNETES OPERATIONS ==========================================================
Downloads · 30 days
0
Access
Public
Updated Aug 25, 2026
Repo size
—
Likes
0
Public
Click a slice to open those files.
.q43.6 KB · 26%
From the Hugging Face model README
A custom model built on DeepReinforce Ornith-1.0-9B/1.5-9B, tuned as an autonomous and automation agent. It speaks the Anthropic-compatible API, so it drives Claude Code, Codex and opencode fully locally
Ornith-1.0-9B scores 69.4% on SWE-Bench Verified , Ornith-1.5-9B scores 70.6% on SWE-Bench Verified - beating models 3-4x larger (Gemma 4-31B, Qwen 3.6-35B) in coding tasks, despite having only 9B parameters.
The model ships with a system prompt focused on real work in a terminal: use tools instead of guessing, write files instead of pasting code, ground every answer in real tool output, and stay terse. Thinking is suppressed (think:false), context set to 256K.
Model | Base | Context | Size | Purpose ornith-k8s:1.0-9b.q4 | Ornith-1.0-9B (GGUF Q4_K_M) | 256K | 5.6 GB | Coding agent, SWE-Bench 69.4%, 32GB+ Apple Silicon ornith-k8s:1.0-9b.q8 | Ornith-1.0-9B (GGUF Q8_K_M) | 256K | 9.5 GB | Coding agent, more precise ornith-k8s:1.5-9b.q4 | Ornith-1.5-9B (GGUF Q4_K_M) | 256K | 5.7 GB | Coding agent, more precise ornith-k8s:1.5-9b.q8 | Ornith-1.5-9B (GGUF Q8_K_M) | 256K | 9.8 GB | Coding agent, more precise
$ ollama run ornith-k8s
In Claude Code: $ ollama launch claude --model ornith-k8s
## User
execute kubectl to get nodes on the current context
---
## Assistant (Build · Ornith K8S · 63.5s)
_Thinking:_
The user wants me to run a simple kubectl command to list nodes. Straightforward.
**Tool: bash**
**Input:**
```json
{
"command": "kubectl get nodes"
}
Output:
NAME STATUS ROLES AGE VERSION
k8s Ready control-plane,worker 473d v1.34.6
temperature 0.2, top_p 0.9, top_k 20, repeat_penalty 1.05, num_ctx 262144 Native context 262K - can be raised on stronger hardware
Duplicate from rafw007/ornith-1.0-9b-claude-coder with adaption for Devops and Kubernetes Operations.
MIT (inherited from the base DeepReinforce Ornith-1.0 model).
--- Card: 2026-08-24. Tests on Mac Mini and opencode