# Jan-v1 (/desktop/jan-models/jan-v1)

## Overview [#overview]

Jan-v1 is a 4B parameter model based on Qwen3-4B-thinking, designed for reasoning and problem-solving tasks. The model achieves 91.1% accuracy on SimpleQA through model scaling and fine-tuning approaches.

<a
  href="jan://models/huggingface/janhq/Jan-v1-4B-GGUF"
  style={{
    display: 'inline-flex',
    alignItems: 'center',
    gap: '8px',
    padding: '10px 20px',
    backgroundColor: '#000',
    color: '#fff',
    borderRadius: '8px',
    fontWeight: '600',
    fontSize: '15px',
    textDecoration: 'none',
    marginTop: '8px',
  }}
>
  Open in Jan
</a>

## Performance [#performance]

### SimpleQA Benchmark [#simpleqa-benchmark]

Jan-v1 demonstrates strong factual question-answering capabilities:

![Jan-v1 SimpleQA Performance](../_assets/simpleqa_jan_v1.png)

At 91.1% accuracy, Jan-v1 outperforms several larger models on SimpleQA, including Perplexity's 70B model. This performance represents effective scaling and fine-tuning for a 4B parameter model.

### Chat and Creativity Benchmarks [#chat-and-creativity-benchmarks]

Jan-v1 has been evaluated on conversational and creative tasks:

![Jan-v1 Creativity Benchmarks](../_assets/creative_bench_jan_v1.png)

These benchmarks (EQBench, CreativeWriting, and IFBench) measure the model's ability to handle conversational nuance, creative expression, and instruction following.

## Requirements [#requirements]

- **Memory**:
  - Minimum: 8GB RAM (with Q4 quantization)
  - Recommended: 16GB RAM (with Q8 quantization)
- **Hardware**: CPU or GPU
- **API Support**: OpenAI-compatible at localhost:1337

## Using Jan-v1 [#using-jan-v1]

### Quick Start [#quick-start]

1. Download Jan Desktop
2. Click **Open in Jan** above, or open the **Hub** and search for Jan-v1
3. Choose a variant that fits your hardware, then click **Download**
4. Once downloaded, select Jan-v1 from the model selector in any chat
5. Start chatting - no additional configuration needed

### Demo [#demo]

![Jan-v1 Demo](https://catalog.jan.ai/docs/jan_v1_demo.gif)

### Deployment Options [#deployment-options]

**Using vLLM:**
```bash
vllm serve janhq/Jan-v1-4B \
    --host 0.0.0.0 \
    --port 1234 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes
```

**Using llama.cpp:**
```bash
llama-server --model jan-v1.gguf \
    --host 0.0.0.0 \
    --port 1234 \
    --jinja \
    --no-context-shift
```

### Recommended Parameters [#recommended-parameters]

```yaml
temperature: 0.6
top_p: 0.95
top_k: 20
min_p: 0.0
max_tokens: 2048
```

## What Jan-v1 Does Well [#what-jan-v1-does-well]

- **Question Answering**: 91.1% accuracy on SimpleQA
- **Reasoning Tasks**: Built on thinking-optimized base model
- **Tool Calling**: Supports function calling through hermes parser
- **Instruction Following**: Reliable response to user instructions

## Limitations [#limitations]

- **Model Size**: 4B parameters limits complex reasoning compared to larger models
- **Specialized Tasks**: Optimized for Q&A and reasoning, not specialized domains
- **Context Window**: Standard context limitations apply

## Available Formats [#available-formats]

### GGUF Quantizations [#gguf-quantizations]

- **Q4_K_M**: 2.5 GB - Good balance of size and quality
- **Q5_K_M**: 2.89 GB - Better quality, slightly larger
- **Q6_K**: 3.31 GB - Near-full quality
- **Q8_0**: 4.28 GB - Highest quality quantization

## Models Available [#models-available]

- [Jan-v1 on Hugging Face](https://huggingface.co/janhq/Jan-v1-4B)
- [Jan-v1 GGUF on Hugging Face](https://huggingface.co/janhq/Jan-v1-4B-GGUF)

## Technical Notes [#technical-notes]

<Callout type="info">
The model includes a system prompt in the chat template by default to match benchmark performance. A vanilla template without system prompt is available in `chat_template_raw.jinja`.
</Callout>

## Community [#community]

- **Discussions**: [HuggingFace Community](https://huggingface.co/janhq/Jan-v1-4B/discussions)
- **Support**: Available through Jan App at [jan.ai](https://jan.ai)