---

license: gemma

base_model: unsloth/gemma-4-E2B-it

tags:

• gguf
• gemma
• mathematics
• latex
• local-model

---

Gifted Maths Gemma 4 GGUF

This is the verified GGUF version of maths_engine, a local gifted mathematics model designed for student-facing step-by-step LaTeX solutions.

Source

• Base model: unsloth/gemma-4-E2B-it
• LoRA adapter: arabellako22/gifted_maths_lora_model
• Verified merged model: arabellako22/gifted_maths_unsloth_remerged_full_gemma_4
• Dataset snapshot: arabellako22/gifted_maths_training_dataset

Files

• gifted-maths-gemma-4-v2.Q4_K_M.gguf: recommended local version
• gifted-maths-gemma-4-v2.Q5_K_M.gguf: slightly larger, usually better quality
• Modelfile: Ollama-compatible template helper

Prompt Format

~~~text

<start_of_turn>system

You are maths_engine, a local gifted mathematics reasoning model for students.

You solve maths problems step by step, clearly and calmly.

All variables, formulas, equations, transformations, and final answers must use LaTeX.

Use inline math with $...$ and display math with $$...$$.

Do not skip algebraic steps when the learner would benefit from seeing them.

End every solution with a clear line starting with: Final Answer:<end_of_turn>

<start_of_turn>user

Solve $2x^2+7x-4=0$ using the quadratic formula.<end_of_turn>

<start_of_turn>model

~~~

llama.cpp example

~~~bash

llama-cli \

-m gifted-maths-gemma-4-v2.Q4_K_M.gguf \

-p "<start_of_turn>system

You are maths_engine, a local gifted mathematics reasoning model for students.

You solve maths problems step by step, clearly and calmly.

All variables, formulas, equations, transformations, and final answers must use LaTeX.

Use inline math with $...$ and display math with $$...$$.

Do not skip algebraic steps when the learner would benefit from seeing them.

End every solution with a clear line starting with: Final Answer:<end_of_turn>

<start_of_turn>user

Solve $2x^2+7x-4=0$ using the quadratic formula.<end_of_turn>

<start_of_turn>model" \

-n 900 \

--temp 0

~~~

Verification Rule

This GGUF should not be considered complete unless:

1. base + adapter verification passes
2. merged full model verification passes
3. local GGUF verification passes
4. re-downloaded GGUF verification passes