livchart/ mistral-nemo-12b-q6:latest

2 Downloads Updated 5 days ago

LivChart-Optimized Analytics Model

ollama run livchart/mistral-nemo-12b-q6

curl http://localhost:11434/api/chat \
  -d '{
    "model": "livchart/mistral-nemo-12b-q6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='livchart/mistral-nemo-12b-q6',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'livchart/mistral-nemo-12b-q6',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 5 days ago

5 days ago

6ac1afb5806d · 10GB ·

model

archllama

·

parameters12.2B

·

quantizationQ6_K

10GB

template

{{- range $i, $m := .Messages }} {{- if eq $m.Role "user" }} [INST]{{- if and $.System (eq $i 0) }}{

237B

system

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

1.6kB

params

{ "num_ctx": 8192, "num_gpu": 40, "num_predict": 2048, "repeat_penalty": 1.05, "

125B

Readme

LivChart Optimized Mistral Nemo 12B Model

This repository contains a custom Mistral Nemo 12B configuration optimized for LivChart AI analytics workflows.

🌐 Website: https://livchart.com

The model is designed to improve:

Dashboard-focused reasoning
Structured chart generation
Analytics response consistency
Turkish business analytics understanding
Metric and filter interpretation
Lower hallucination rate in BI workflows

What Is This?

This is not a fine-tuned model.

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

The optimization layer includes:

Custom system prompts
Analytics-focused response behavior
Dashboard workflow specialization
Structured output improvements
Chart-oriented instruction tuning

VRAM Optimization

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

Recommended for:

RTX 4070 Ti SUPER
RTX 4080 / 4090
RTX 5080
Radeon 7900 XTX
Similar high-memory GPUs

The setup is designed to balance:

Fast dashboard generation
Stable structured output
Responsive analytics workflows
Efficient local inference performance

Base Model

Model Family: Mistral Nemo 12B
Quantization: Q6
Runtime: Ollama
Configuration Method: Modelfile

# LivChart Optimized Mistral Nemo 12B Model

This repository contains a custom Mistral Nemo 12B configuration optimized for LivChart AI analytics workflows.

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

The model is designed to improve:

- Dashboard-focused reasoning
- Structured chart generation
- Analytics response consistency
- Turkish business analytics understanding
- Metric and filter interpretation
- Lower hallucination rate in BI workflows

---

# What Is This?

This is not a fine-tuned model.

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

The optimization layer includes:

- Custom system prompts
- Analytics-focused response behavior
- Dashboard workflow specialization
- Structured output improvements
- Chart-oriented instruction tuning

---

# VRAM Optimization

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

Recommended for:

- RTX 4070 Ti SUPER
- RTX 4080 / 4090
- RTX 5080
- Radeon 7900 XTX
- Similar high-memory GPUs

The setup is designed to balance:

- Fast dashboard generation
- Stable structured output
- Responsive analytics workflows
- Efficient local inference performance

---

# Base Model

- Model Family: Mistral Nemo 12B
- Quantization: Q6
- Runtime: Ollama
- Configuration Method: Modelfile

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