myvotrexian/ voxy-gemma4:q5-base-chat

7 Downloads Updated 5 days ago

vision tools thinking

ollama run myvotrexian/voxy-gemma4:q5-base-chat

curl http://localhost:11434/api/chat \
  -d '{
    "model": "myvotrexian/voxy-gemma4:q5-base-chat",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='myvotrexian/voxy-gemma4:q5-base-chat',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'myvotrexian/voxy-gemma4:q5-base-chat',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 5 days ago

5 days ago

0a9e32966ec0 · 3.6GB ·

model

archgemma4

·

parameters4.65B

·

quantizationQ5_K_M

3.6GB

system

Kamu adalah Voxy, AI companion yang hangat, santai, dan diciptakan oleh Votrexian. ATURAN STRICT: -

275B

params

{ "stop": [ "<end_of_turn>", "<start_of_turn>" ], "temperature": 0.3,

96B

Readme

🤖 Voxy Model Suite

Voxy adalah AI companion & tactical analyst berbasis Gemma-4 E2B yang dioptimalkan untuk respons cepat, percakapan santai, dan analisis strategi/gaming mechanics yang kompleks.

Repositori ini menampung seluruh ekosistem varian model Voxy, mulai dari versi base text-only hingga versi multimodal vision dan specialist tactical analyst.

🏷️ Model Variants & Tags

Tag	Capabilities	Vision Support	Best For
`q5-base-chat`	Text Only	❌ No	General lightweight chatting, text-based data analysis, & low-RAM devices.
`q5-visionary-chat`	Multimodal	👁️ Yes	General assistant with image recognition capabilities.
`q5-game-visionary`	Gaming Specialist	👁️ Yes	Flagship: Deep gaming mechanics knowledge, loadout/fitting analysis, & screenshot OCR.

⚡ Quick Start

Jalankan varian yang kamu butuhkan langsung via Ollama CLI:

ollama run myvotrexian/voxy:q5-base-chat ollama run myvotrexian/voxy:q5-game-visionary

📊 System Requirements & Benchmarks

Quantization: Q5_K_M (5-bit K-Quant Medium)
Context Length: Default 2048 / 4096 tokens
Memory Footprint:
- Text Mode: ~3.6 GB - 3.8 GB (RAM/VRAM)
- Vision Mode: ~4.6 GB (saat membaca file gambar)

Target Environment	Inference Speed
Nvidia RTX 3050 Mobile (4GB VRAM)	~30 - 45+ tokens/s
My Micro Server (2-Core CPU)	~7 - 10 tokens/s

🛠️ Maintainer

Developed & Maintained with ❤️ by Votrexian / ATom.

# 🤖 Voxy Model Suite

**Voxy** adalah AI companion & tactical analyst berbasis **Gemma-4 E2B** yang dioptimalkan untuk respons cepat, percakapan santai, dan analisis strategi/gaming mechanics yang kompleks.

Repositori ini menampung seluruh ekosistem varian model Voxy, mulai dari versi *base text-only* hingga versi *multimodal vision* dan *specialist tactical analyst*.

---

## 🏷️ Model Variants & Tags

| Tag | Capabilities | Vision Support | Best For |
| :--- | :--- | :--- | :--- |
| **`q5-base-chat`** | Text Only | ❌ No | General lightweight chatting, text-based data analysis, & low-RAM devices. |
| **`q5-visionary-chat`** | Multimodal | 👁️ Yes | General assistant with image recognition capabilities. |
| **`q5-game-visionary`** | **Gaming Specialist** | 👁️ Yes | **Flagship**: Deep gaming mechanics knowledge, loadout/fitting analysis, & screenshot OCR. |

---

## ⚡ Quick Start

Jalankan varian yang kamu butuhkan langsung via Ollama CLI:

ollama run myvotrexian/voxy:q5-base-chat
ollama run myvotrexian/voxy:q5-game-visionary

---

## 📊 System Requirements & Benchmarks

* **Quantization**: `Q5_K_M` (5-bit K-Quant Medium)
* **Context Length**: Default 2048 / 4096 tokens
* **Memory Footprint**:
  * **Text Mode**: ~3.6 GB - 3.8 GB (RAM/VRAM)
  * **Vision Mode**: ~4.6 GB (saat membaca file gambar)

| Target Environment | Inference Speed |
| :--- | :--- |
| **Nvidia RTX 3050 Mobile (4GB VRAM)** | ~30 - 45+ tokens/s |
| **My Micro Server (2-Core CPU)** | ~7 - 10 tokens/s |

---

## 🛠️ Maintainer
Developed & Maintained with ❤️ by **Votrexian / ATom**.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)