SetneufPT/ Gemma4-12B_Q4_64K_16GB-GPU:latest

455 1 week ago

Custom model for coding with agents to use locally with 16gb or 2x8gb GPUs (working fine...)

tools thinking 
ollama run SetneufPT/Gemma4-12B_Q4_64K_16GB-GPU

Details

1 week ago

6a6b9bcd04fb · 6.8GB ·

model
gemma4
·
11.9B
·
Q4_K_S
license
Credits to Danielhanchen. Base model: Gemma 4 12B
system
You are a coding agent. Be concise. Avoid loops. Use tools only when necessary. Do not repeat the sa
params
{ "num_ctx": 64000, "repeat_last_n": 4096, "repeat_penalty": 1.1, "seed": 79, "s

Readme

Gemma 4 - 12B param, Q4, 64K ctx, Local/Offline, 16GB (or 2x 8GB) GPU

Custom Ollama model, fine-tuned from Gemma4 12b from Unsloth, configured for local coding-agent workflows, especially with Open Code or Hermes.

This model is based on a 12B parameter LLM, quantized in Q4, and configured with a large context window for software development tasks. It is intended to provide a practical balance between performance, memory usage, and code-assistance quality on local hardware.

Model details

  • Type: Text model
  • Size: 12B parameters
  • Quantization: Q4
  • Context target: 64K
  • Real GPU memory usage: 8,2 GB VRAM
  • Recommended GPU memory: 16 GB VRAM
  • Main focus: Coding and agentic development workflows
  • Tool use: Supported, depending on the client/application
  • Thinking/reasoning mode: Supported, depending on the client/application

Intended use

This model is designed for:

  • Agents workflows
  • Local coding assistants
  • Code analysis
  • Debugging support
  • Refactoring suggestions
  • Project exploration
  • Terminal-based programming tasks
  • Educational demonstrations of AI coding agents

image.png