livchart/ qwen3.5-9b-q6:latest

10 Downloads Updated 5 days ago

LivChart-Optimized Analytics Model

ollama run livchart/qwen3.5-9b-q6

curl http://localhost:11434/api/chat \
  -d '{
    "model": "livchart/qwen3.5-9b-q6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='livchart/qwen3.5-9b-q6',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'livchart/qwen3.5-9b-q6',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 5 days ago

5 days ago

6d4edac0916e · 7.4GB ·

model

archqwen35

·

parameters8.95B

·

quantizationQ6_K

7.4GB

template

{{- if .System }} <|im_start|>system {{ .System }}<|im_end|> {{- end }} {{- range .Messages }} {{- i

470B

system

You are the AI engine behind LivChart. Your responsibilities include: - generating charts - interpre

1.6kB

params

{ "num_ctx": 8192, "num_gpu": 33, "num_predict": 2048, "repeat_penalty": 1.05, "

157B

Readme

LivChart Optimized Qwen3.5 Model

This repository contains a custom Qwen3.5 model configuration optimized for LivChart AI analytics workflows.

🌐 Website: https://livchart.com

The model is designed to improve:

Chart generation consistency
Structured analytics output
Dashboard-oriented responses
Turkish business analytics understanding
Filter and metric interpretation
Lower hallucination rate in chart workflows

What Is This?

This is not a fine-tuned model.

Instead, it is a customized Qwen3.5 runtime configuration created using a Modelfile.

The optimization layer includes:

Custom system prompts
Response behavior tuning
Analytics-focused instruction design
Structured output improvements
LivChart workflow specialization

VRAM Optimization

This configuration is optimized for systems with approximately 16 GB VRAM.

Recommended for:

RTX 4080 / 4090
RTX 5080
Radeon 7900 XTX
Similar high-memory GPUs

The setup is designed to balance:

Fast analytics response generation
Stable structured output
Large context handling
Lower latency during dashboard workflows

Base Model

Model Family: Alibaba Cloud Qwen3.5
Runtime: Ollama
Configuration Method: Modelfile

# LivChart Optimized Qwen3.5 Model

This repository contains a custom Qwen3.5 model configuration optimized for LivChart AI analytics workflows.

🌐 Website: [https://livchart.com](https://livchart.com)

The model is designed to improve:

- Chart generation consistency
- Structured analytics output
- Dashboard-oriented responses
- Turkish business analytics understanding
- Filter and metric interpretation
- Lower hallucination rate in chart workflows

---

# What Is This?

This is not a fine-tuned model.

Instead, it is a customized Qwen3.5 runtime configuration created using a Modelfile.

The optimization layer includes:

- Custom system prompts
- Response behavior tuning
- Analytics-focused instruction design
- Structured output improvements
- LivChart workflow specialization

---

# VRAM Optimization

This configuration is optimized for systems with approximately **16 GB VRAM**.

Recommended for:

- RTX 4080 / 4090
- RTX 5080
- Radeon 7900 XTX
- Similar high-memory GPUs

The setup is designed to balance:

- Fast analytics response generation
- Stable structured output
- Large context handling
- Lower latency during dashboard workflows

---

# Base Model

- Model Family: Alibaba Cloud Qwen3.5
- Runtime: Ollama
- Configuration Method: Modelfile

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