shafire/Zero-Gemma4-E4B-OpenZero-GGUF

[image]

<p align="center"> <img src="./zero-model-avatar.png" width="150" alt="Zero OpenZero AI model"> </p>

ZERO Gemma 4 E4B OpenZero — Standalone Compact Agentic GGUF

<p align="center"> <strong>COMPACT ZERO. FULL STANDALONE MODEL. ONE DOWNLOAD.</strong><br> Local research, coding and autonomous workflows without adapter setup. </p>

Zero Gemma 4 E4B OpenZero is a standalone, merged GGUF model for compact local AI deployments. The trained OpenZero weights are already fused into the model. There is no separate LoRA adapter and no second base-model download.

Small enough to run locally. Sharp enough to be Zero.

OpenZero 7.1 demo


[▶ Watch “OpenZero 7.1 — 16 Agents, 1 LLM” on YouTube](https://www.youtube.com/watch?v=qmAR7UgFJAo)

The demo shows the local-first OpenZero control panel running a 16-agent autonomy configuration around one local LLM.

OpenZero local model family

This release is one of the three local model choices shown in the current OpenZero and ZeroThink interfaces:

Run directly from Hugging Face with Ollama:

ollama run hf.co/shafire/Zero-Gemma4-E4B-OpenZero-GGUF
ollama run hf.co/shafire/Zero-Qwen3-8B-OpenZero-GGUF:Q5_K_M

OpenZero 7.1 can select the installed aliases locally. ZeroThink can route through its OpenZero Local provider when connected to an OpenZero node. Alias availability depends on which quantizations are installed on the machine.

OpenZero in action

<table> <tr> <td align="center" width="32%"> <img src="./openzero-7-1-ultra-16-agents.png" alt="OpenZero 7.1 panel showing Ultra mode and a 16-agent setting"> <br>_{OpenZero 7.1 — Ultra autonomy with the 16-agent setting.} </td> <td align="center" width="68%"> <img src="./zerothink-openzero-model-selector.png" alt="ZeroThink Studio OpenZero local model selector"> <br>_{ZeroThink Studio — the three current OpenZero local model choices.} </td> </tr> <tr> <td align="center" colspan="2"> <img src="./openzero-local-agent-response.png" alt="OpenZero local Agent Zero response"> <br>_{Local Agent Zero response inside the OpenZero control panel.} </td> </tr> <tr> <td align="center" colspan="2"> <img src="./openzero-agentic-workflow.png" alt="OpenZero agentic workflow in the Super Panel"> <br>_{OpenZero agentic workflow and local privacy controls.} </td> </tr> </table>

Download this model

• —Standalone model: yes
• —Separate adapter required: no
• —Separate base model required: no
• —llama.cpp compatible: yes
• —OpenZero compatible: yes
• —CPU generation tested: yes

The file retains the Q5KM base tensors while preserving the 66 trained attention tensors in F16. That keeps the fine-tuned tensors at higher precision without forcing a second lossy quantization pass across the whole model.

What Zero is built for

• —Compact agentic AI: planning, structured execution and verification
• —Coding: debugging, implementation guidance, review and test design
• —Research: careful synthesis, evidence checks and explicit uncertainty
• —Tool workflows: deciding what to inspect, change and verify next
• —Local privacy: CPU-friendly inference without a hosted model dependency
• —OpenZero: OpenAI-compatible local serving for autonomous systems

Run with llama.cpp

llama-cli \
  -m Zero-Gemma4-E4B-OpenZero-Q5_K_M-F16-Merged.gguf \
  --jinja -c 8192 -t 8

Start an OpenAI-compatible endpoint for OpenZero:

llama-server \
  -m Zero-Gemma4-E4B-OpenZero-Q5_K_M-F16-Merged.gguf \
  --jinja -c 8192 -t 8 \
  --host 127.0.0.1 --port 8080

Use http://127.0.0.1:8080/v1 as the local OpenAI-compatible API base.

Run with Ollama

Create Modelfile beside the GGUF:

FROM ./Zero-Gemma4-E4B-OpenZero-Q5_K_M-F16-Merged.gguf
PARAMETER temperature 0.7
PARAMETER top_p 0.95
PARAMETER num_ctx 8192

ollama create zero-gemma4 -f Modelfile
ollama run zero-gemma4

Real CPU benchmark

Measured locally with llama-bench from llama.cpp b10107:

This old-CPU result is a reproducible deployment reference, not a universal speed claim. Modern CPUs and GPU offload should perform differently.

Verified release

• —Base: unsloth/gemma-4-E4B-it
• —Full fine-tuning run: 2,033 curated OpenZero examples
• —Train / validation split: 1,972 / 61
• —Final reported train loss: 1.66231323
• —Validation loss at step 50: 1.287308
• —Validation mean token accuracy at step 50: 0.681814
• —Trainable LoRA parameters: 2,269,184
• —Fusion: 66 trained tensors merged; 720 tensors written
• —SHA-256: 84fd62ff6c5f0abe14dd2c6135e56800df4bc4a0b9d4cd8d9f26c36b28aa190b
• —CPU load and text-generation smoke test: PASS

The training material is already represented in the merged weights. Users do not need the dataset, the training archive or a LoRA adapter to run this model.

Practical notes

• —Start with an 8K context on a 16 GiB system and increase it only after measuring available memory.
• —This release is text-only. A multimodal projector is not included or required.
• —Tool execution is provided by the surrounding OpenZero or agent runtime.
• —The 512-token fine-tuning window strengthened targeted behavior; it does not redefine all long-context behavior inherited from the base.
• —Validate high-stakes outputs independently.

OpenZero

Zero Gemma is the compact member of the Zero model family: local-first, agent-oriented and built to verify before it boasts.

• —Model creator: shafire
• —OpenZero 7.1: openzero.talktoai.org
• —Related models: Agentic GGUF Models collection

Research. Code. Act. Verify.