Instructions to use jsantillana/vectrayx-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jsantillana/vectrayx-vision with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jsantillana/vectrayx-vision",
	filename="vectrayx-vision-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jsantillana/vectrayx-vision with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jsantillana/vectrayx-vision:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jsantillana/vectrayx-vision:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jsantillana/vectrayx-vision:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf jsantillana/vectrayx-vision:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf jsantillana/vectrayx-vision:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jsantillana/vectrayx-vision:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf jsantillana/vectrayx-vision:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jsantillana/vectrayx-vision:Q4_K_M

Use Docker

docker model run hf.co/jsantillana/vectrayx-vision:Q4_K_M

LM Studio
Jan

vLLM

How to use jsantillana/vectrayx-vision with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jsantillana/vectrayx-vision"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jsantillana/vectrayx-vision",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/jsantillana/vectrayx-vision:Q4_K_M

Ollama
How to use jsantillana/vectrayx-vision with Ollama:
```
ollama run hf.co/jsantillana/vectrayx-vision:Q4_K_M
```

Unsloth Studio

How to use jsantillana/vectrayx-vision with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jsantillana/vectrayx-vision to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jsantillana/vectrayx-vision to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jsantillana/vectrayx-vision to start chatting

How to use jsantillana/vectrayx-vision with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jsantillana/vectrayx-vision:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jsantillana/vectrayx-vision:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jsantillana/vectrayx-vision with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf jsantillana/vectrayx-vision:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jsantillana/vectrayx-vision:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use jsantillana/vectrayx-vision with Docker Model Runner:
```
docker model run hf.co/jsantillana/vectrayx-vision:Q4_K_M
```

Lemonade

How to use jsantillana/vectrayx-vision with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jsantillana/vectrayx-vision:Q4_K_M

Run and chat with the model

lemonade run user.vectrayx-vision-Q4_K_M

List all available models

lemonade list

VectraYX Vision

VectraYX Vision is a Vision-Language Model (VLM) for technical cybersecurity in Spanish, fine-tuned from Gemma 4 E4B-it using LoRA on a 99k-example multimodal corpus.

Quick Start

Ollama

ollama run jsantillana/vectrayx-vision

llama.cpp / LM Studio

Download vectrayx-vision-Q4_K_M.gguf from this repo (~5.3 GB).

llama-cli -m vectrayx-vision-Q4_K_M.gguf -p "Analyze this CVE: CVE-2024-1234" -n 512

Transformers

from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

model = AutoModelForImageTextToText.from_pretrained(
    "jsantillana/vectrayx-vision",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
processor = AutoProcessor.from_pretrained("jsantillana/vectrayx-vision")

Model Details

Field	Value
Base model	google/gemma-4-E4B-it
Architecture	Gemma4ForConditionalGeneration
Parameters	~4B
Context length	131,072 tokens
Fine-tuning	LoRA r=32, alpha=64, 3 epochs
Languages	Spanish (LATAM), English
Modalities	Text + Vision

Training Data

99,175 training records in {messages, image_path} format:

Split	Records	Description
Vision QA	76,655	(synthetic PIL image, question/answer) pairs across 10 domains
Nano SFT replay	22,520	Text-only cybersec ES — prevents catastrophic forgetting

Vision QA Domains

Domain	Records
offense (exploits, web, payloads)	31,521
re (reverse engineering, IDA, Ghidra)	15,788
soc (SIEM, logs, threat intel)	15,303
asm (x86/x64, NASM, kernel)	5,730
forensics (Volatility, DFIR)	2,254
arch (RISC-V, computer architecture)	1,973
icpc (Codeforces, algorithms)	1,302
latam (ES tech blogs, OWASP)	1,264
debugging (x64dbg, WinDbg)	927
crypto (applied cryptography)	593

Images are synthetic PIL renders (not real screenshots) using 19 templates: ida_disasm, ghidra_decomp, gdb_session, siem_dashboard, wireshark_packets, cve_card, terminal_ansi, and more.

Benchmarks

Evaluated with the VectraYX-Vision harness (SageMaker ml.g5.xlarge):

Benchmark	Score	Description
B1 CVE-QA	0.820	CVE analysis in Spanish
B2 Classification	0.420	Threat classification
B3 Commands	0.590	Technical command generation
B4 Tool-use	0.553	Native function calling
B5 Conversational ES	1.000	Spanish conversational fluency
LATAM	0.947	Regional LATAM Spanish (slang, acronyms, code-switching)

Files

File	Size	Description
`model-0000{1-4}-of-00004.safetensors`	~15 GB total	Full bf16 weights
`vectrayx-vision-Q4_K_M.gguf`	5.3 GB	Q4_K_M quantized for local inference

About VectraYX

VectraYX is an open-weights model family optimized for Latin American Spanish, focused on technical cybersecurity and threat analysis.

VectraYX Nano — 130M text model
VectraYX Vision — this model (4B, multimodal)

Downloads last month: 247

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for jsantillana/vectrayx-vision

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Adapter

(108)

this model