Jan-v3-4B

Jan-v3-4B-base-instruct is a compact 4B parameter model created via post-training distillation from a larger teacher model. It is designed as an ownable, general-purpose base that is straightforward to fine-tune, with strong instruction following out of the box.

OverviewCopy Anchor Link

CapabilitiesCopy Anchor Link

• Instruction following: Strong compliance with user instructions out of the box
• Fine-tuning base: Designed as a starting point for downstream fine-tuning
• Coding assistance: Effective lightweight coding help (a dedicated code variant, Jan-Code-4B, is also available)
• General purpose: Distillation preserves broad capabilities across standard benchmarks

PerformanceCopy Anchor Link

Aider Benchmark (Polyglot Code Editing)Copy Anchor Link

Jan-v3-4B leads its weight class on the Aider polyglot benchmark with a strict pass rate of 18, nearly 50% higher than the next best model (Qwen3-4B-Thinking at 12.1):

General Performance ComparisonCopy Anchor Link

Jan-v3-4B-base-instruct outperforms Qwen3-4B-Instruct-2507 (its base) across coding, math, and instruction-following benchmarks while remaining competitive on reasoning:

RequirementsCopy Anchor Link

• 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-v3-4BCopy Anchor Link

Quick StartCopy Anchor Link

1. Download Jan Desktop
2. Click Open in Jan above, or open the Hub and search for Jan-v3-4B-base-instruct
3. Choose a variant that fits your hardware, then click Download
4. Once downloaded, select Jan-v3-4B-base-instruct from the model selector in any chat
5. Start chatting — no additional configuration needed

DemoCopy Anchor Link

Try it live at chat.jan.ai

Deployment OptionsCopy Anchor Link

Using vLLM:

vllm serve janhq/Jan-v3-4B-base-instruct \
    --host 0.0.0.0 \
    --port 1234 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes

Using llama.cpp:

llama-server --model Jan-v3-4B-base-instruct-Q8_0.gguf \
    --host 0.0.0.0 \
    --port 1234 \
    --jinja \
    --no-context-shift

Recommended ParametersCopy Anchor Link

temperature: 0.7
top_p: 0.8
top_k: 20

What Jan-v3-4B Does WellCopy Anchor Link

• Long context: Native 262k token context window for handling large documents
• Instruction following: Reliable and consistent response to user instructions
• Fine-tuning: Designed to be a strong, ownable starting point for specialization
• General tasks: Broad capabilities preserved through distillation from a larger model

LimitationsCopy Anchor Link

• Model size: 4B parameters limit complex multi-step reasoning compared to larger models
• Specialized domains: For coding specifically, consider Jan-Code-4B

Available FormatsCopy Anchor Link

GGUF QuantizationsCopy Anchor Link

• Q4_K_M: Good balance of size and quality
• Q5_K_M: Better quality, slightly larger
• Q8_0: Highest quality quantization (recommended)

Models AvailableCopy Anchor Link

• Jan-v3-4B-base-instruct on Hugging Face

CommunityCopy Anchor Link

• Discussions: HuggingFace Community
• Support: Available through Jan App at jan.ai