Open Brain
arXivPaperNeeds Review

Fine-Tuning Gemma 4 Edge Models for MATLAB Signal-Processing Code with SFT and QLoRA on a Laptop iGPU

Fine-tuning Gemma 4 Edge models improved checked MATLAB signal-processing code on a laptop iGPU, with an adapter adding 17–19% generation-time cost. Gains focused on conventions, not signal construction.

arXiv · Nov 17, 2026
Open Source Open MarkdownOpen JSON
Source Summary

The study fine-tuned Gemma 4 Edge E2B and E4B on **66** checked examples covering 11 MATLAB signal-processing subtasks, then deployed int8 models with adapters through OpenVINO. E2B rose from 18/66 to 37/66 passing tasks; E4B with QLoRA rose from 32/66 to 47/66.

Practical Implication

For a narrow offline coding workload, a small task-specific dataset and deterministic checks may make local adaptation practical. Inspect failure categories before expanding training data: the reported adapters mostly fixed conventions such as units, array shapes, and lag signs.

Agent-Ready Context
The study fine-tuned Gemma 4 Edge E2B and E4B on **66** checked examples covering 11 MATLAB signal-processing subtasks, then deployed int8 models with adapters through OpenVINO. E2B rose from 18/66 to 37/66 passing tasks; E4B with QLoRA rose from 32/66 to 47/66.

For a narrow offline coding workload, a small task-specific dataset and deterministic checks may make local adaptation practical. Inspect failure categories before expanding training data: the reported adapters mostly fixed conventions such as units, array shapes, and lag signs.

The adapters fixed few errors in building signals and noise, and cost **17–19%** of generation speed at runtime. Results are from one set of subtasks and held-out variants, not general MATLAB coding.
Connected Context · Feed7 Judgment

This provides a bounded example of local task adaptation producing measurable gains on checked coding tasks, while exposing runtime cost and error types that adapters did not fix. It makes the open-model customization case more concrete but does not establish broader coding ability or general deployment value.

Data Quality Is the Compute Multiplier — Ari Morcos, DatologyAIThe candidate argues that task-matched, curated data can matter more than added compute; this study gives a narrow example where a small checked dataset improved a specific workload, with remaining errors pointing to limits in what the data and adaptation addressed.unslothai/unslothThe candidate describes tooling for local model training and serving; this Signal adds a concrete laptop-scale adaptation result and a measured generation-speed cost that would matter when evaluating that workflow.Local Models: Trust, Control, Optimization — Carter Abdallah, NVIDIAThe candidate frames open models around ownership and training control; this study shows one practical use of that control, but its narrow task results and runtime overhead bound the case for local adaptation.
Context Map
modelcodingdata#open-models#model-selection
Uncertainty
The adapters fixed few errors in building signals and noise, and cost **17–19%** of generation speed at runtime. Results are from one set of subtasks and held-out variants, not general MATLAB coding.