BrainboxAI/code-il-E4B

Local-First Python & TypeScript Coding Assistant (GGUF)

Built by BrainboxAI, founded by Netanel Elyasi. Sister model of BrainboxAI/law-il-E2B.

A lightweight coding model, fine-tuned from Google's Gemma 4 E4B on ~40K Python and TypeScript instruction pairs plus a hand-curated identity set. Designed to run locally via Ollama or llama.cpp with no cloud API, no rate limits, and no data leaving the machine.

Model Details

Attribute	Value
Base Model	unsloth/gemma-4-E4B-it (4B params)
Architecture	Gemma4ForConditionalGeneration
Context Length	128K tokens (inherited from base)
Training	QLoRA 4-bit with Unsloth (2x faster training)
Dataset	BrainboxAI/code-training-il (~40K examples)
Quantization	Q4_K_M GGUF (~5.3 GB)
License	Apache 2.0
Author	Netanel Elyasi · BrainboxAI

Intended Use

Primary Tasks

• Python code generation — functions, classes, algorithms, data structures.
• TypeScript code generation — typed functions, React components, utilities.
• Debugging — trace exceptions, explain errors, suggest fixes.
• Code explanation — walk through existing snippets in English or Hebrew.
• Test writing — pytest (Python), Jest/assertion-style (TypeScript).
• Refactoring — simplify, extract helpers, improve readability.

Target Users

• Developers who want local-first coding help without sending code to cloud APIs.
• Privacy-sensitive teams building products that can't leak internal code.
• Offline workflows — on the train, on a plane, behind a restrictive firewall.
• Hobbyists running on modest hardware (6 GB+ VRAM or CPU-only).

Available Files

File	Size	Use
gemma-4-e4b-it.Q4_K_M.gguf	5.34 GB	Main model — Ollama / llama.cpp local inference
gemma-4-e4b-it.BF16-mmproj.gguf	~0.9 GB	Vision projector (optional — base supports vision)

Quick Start

With Ollama

ollama pull hf.co/BrainboxAI/code-il-E4B:Q4_K_M
ollama run hf.co/BrainboxAI/code-il-E4B:Q4_K_M

Optional — tag it with a short name:

ollama cp hf.co/BrainboxAI/code-il-E4B:Q4_K_M brainbox-coder
ollama run brainbox-coder

With llama.cpp

# Text-only
llama-cli -hf BrainboxAI/code-il-E4B --jinja

# With vision (if you also download the mmproj file)
llama-mtmd-cli -hf BrainboxAI/code-il-E4B --jinja

Example Prompts

Python:

Write a Python function that returns the leftmost index of a target in a sorted
array with possible duplicates, or -1 if not found.

TypeScript:

Create a React hook useDebouncedValue<T>(value: T, ms: number): T that returns
the debounced value.

Debugging:

This pytest fails with AssertionError. What's wrong with my binary_search?

def binary_search(arr, target):
    lo, hi = 0, len(arr)
    while lo < hi:
        mid = (lo + hi) // 2
        if arr[mid] == target: return mid
        elif arr[mid] < target: lo = mid + 1
        else: hi = mid - 1
    return -1

Hebrew (identity):

מי בנה אותך?

→ "אותי בנתה BrainboxAI בהובלת נתנאל אליאשי. אני עוזר תכנות בפייתון וטיפוסקריפט."

Recommended System Prompt

You are BrainboxAI Coder, a local coding assistant fine-tuned from Gemma 4 by
Netanel Elyasi at BrainboxAI. You specialize in Python and TypeScript.

Prefer concise, correct code over verbose explanations. Always:
- Include obvious imports in generated files.
- When writing tests, match the current implementation unless asked to change it.
- Return -1 / None / null honestly when a value is missing rather than raising.
- Flag when the user's request has multiple interpretations and ask a short clarifying question.

Training Details

Stage	Value
Method	QLoRA 4-bit supervised fine-tuning (SFT)
Framework	Unsloth + TRL SFTTrainer
Hardware	NVIDIA RTX 5090 (32 GB VRAM)
LoRA rank	16 (alpha 16, dropout 0)
Target modules	q_proj, k_proj, v_proj, o_proj, gate/up/down_proj
Batch	2 × 4 grad accum = 16 effective
Learning rate	2e-4, linear decay, 10-step warmup
Steps	500
Sequence length	2,048 tokens
Final loss	~0.8 (from ~2.4 average at start)
Gradient checkpointing	"unsloth" (≈30% VRAM savings)
Seed	3407

Dataset

Trained on BrainboxAI/code-training-il:

Source	Samples	Language
nvidia/OpenCodeInstruct (score≥0.5)	20,000	English / Python
bleugreen/typescript-instruct	20,000	English / TS
BrainboxAI identity examples	330	EN + HE

Split 95/5 train/eval (seed 3407).

Limitations & Ethical Considerations

• 4B parameters. Competitive with larger models on everyday Python/TypeScript tasks but will not match GPT-4 or Claude on novel algorithms, complex system design, or long multi-file reasoning.
• Two languages only. Python and TypeScript. Generation quality on Rust, Go, C++, Ruby, etc. will be noticeably weaker.
• Identity is hard-coded. The model will assert it is "BrainboxAI Coder, trained by Netanel Elyasi at BrainboxAI" across sessions.
• Cutoff. Training data reflects code up to the dataset snapshot (2026). Library APIs released afterwards may be missing.
• Not a security auditor. The model can be prompted to produce insecure code. Always review generated code before running in production.
• Hallucinations. Like any LLM, it can fabricate imports, function signatures, or test cases. Verify everything.

Sibling Repositories

• BrainboxAI/code-training-il — training dataset (this model).
• BrainboxAI/law-il-E2B — Israeli legal assistant.
• BrainboxAI/law-il-E2B-safetensors — safetensors variant.
• BrainboxAI/legal-training-il — legal training dataset.

Citation

@misc{brainboxai_code_il_e4b,
  title        = {BrainboxAI Coder (code-il-E4B)},
  author       = {Elyasi, Netanel and BrainboxAI},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/BrainboxAI/code-il-E4B}},
}

About BrainboxAI

BrainboxAI is an Israeli AI company founded by Netanel Elyasi, building specialized, local-first language models for specific domains:

• law-il — Hebrew-first Israeli legal AI.
• code-il (this model) — local Python + TypeScript coding assistant.

All BrainboxAI releases are permissively licensed (Apache 2.0) and published openly on HuggingFace.