JA

Jan Code 4b

JanGGUF by bartowskiUpdated 2026-03-03
Download on Hugging Face
Parameters4.41B
Context256K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

Jan Code 4b needs about 4.5 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 8.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Jan Code 4b – a lightweight coding model built on Qwen3

Jan Code 4b is a 4.41 billion‑parameter model tuned for coding tasks. It is designed for local deployment with low latency and compute requirements. The model supports generation, editing, refactoring, and debugging of code.

Good at

  • Code generation
  • Code editing
  • Debugging

Limits

  • No vision support
  • Limited to coding and tools
  • Requires 8 k context for estimates

Best for

  • Local coding assistant
  • Agentic workflow worker
  • Replacing Haiku in Claude Code

Who it’s for. Developers and researchers who need a fast, local coding model for everyday tasks or as a lightweight worker in larger agentic systems. The model is suitable for those who prefer open‑source solutions and can run it on modest hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ2_M1.7 GB 3.4 GB
Fits Get file →
Q2_K1.8 GB 3.5 GB
Fits Get file →
IQ3_XXS1.8 GB 3.5 GB
Fits Get file →
IQ3_XS2.0 GB 3.7 GB
Fits Get file →
Q3_K_S2.1 GB 3.8 GB
Fits Get file →
IQ3_M2.1 GB 3.8 GB
Fits Get file →
Q2_K_L2.2 GB 3.9 GB
Fits Get file →
Q3_K_M2.2 GB 4.0 GB
Fits Get file →
Q3_K_L2.4 GB 4.1 GB
Fits Get file →
IQ4_XS2.5 GB 4.2 GB
Fits Get file →
Q4_02.6 GB 4.3 GB
Fits Get file →
IQ4_NL2.6 GB 4.3 GB
Fits Get file →
Q4_K_S2.6 GB 4.4 GB
Fits Get file →
Q3_K_XL2.7 GB 4.5 GB
Fits Get file →
Q4_K_M2.8 GB 4.5 GB
Fits Get file →
Q4_12.8 GB 4.5 GB
Fits Get file →
Q4_K_L3.1 GB 4.8 GB
Fits Get file →
Q5_K_S3.1 GB 4.8 GB
Fits Get file →
Q5_K_M3.3 GB 5.0 GB
Fits Get file →
Q5_K_L3.5 GB 5.2 GB
Fits Get file →
Q6_K3.7 GB 5.4 GB
Fits Get file →
Q6_K_L3.9 GB 5.6 GB
Fits Get file →
Q8_04.7 GB 6.4 GB
Fits Get file →
BF168.8 GB 10.5 GB
Too big Get file →

For 8 GB VRAM, the IQ2_M quant (~3.4 GB memory) is a good choice. If you have 12 GB VRAM, Q4_0 (~4.3 GB memory) offers better quality. For 16 GB VRAM, Q5_K_L (~5.2 GB memory) provides a balance of size and performance.

What GPU do you need for Jan Code 4b?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q3_K_M (2.2 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K_L (3.9 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.7 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.8 GB file, about 10.5 GB in use).

Which Jan Code 4b quant should you choose?

Q4_K_M is the usual starting point for Jan Code 4b: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 4.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.41B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized bybartowski
FamilyJan
Licenseapache-2.0
Downloads (HF)1,186
Last updated2026-03-03

Frequently asked questions about Jan Code 4b

How much VRAM does Jan Code 4b need?

About 4.5 GB at Q4_K_M with an 8K context window. That is the 2.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Jan Code 4b on an 8 GB GPU?

Yes, with Q8_0: the 4.7 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Jan Code 4b GGUF?

It depends on the quant: file is 0.0 GB, IQ2_M is 1.7 GB, Q2_K is 1.8 GB, IQ3_XXS is 1.8 GB, IQ3_XS is 2.0 GB, Q3_K_S is 2.1 GB and 19 more.

What context length does Jan Code 4b support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Jan Code 4b GGUF?

The files are on Hugging Face in the bartowski/janhq_Jan-code-4b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Jan Code 4b use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Jan Code 4b on 8 GB VRAM?

Yes, using the IQ2_M quant which requires approximately 3.4 GB of VRAM at 8 k context.

Does Jan Code 4b support image inputs?

No, the model does not have vision capabilities.

Other GGUFs of Jan-code-4b

Similar models

Browse all →

More from bartowski

All by bartowski →

More Jan models

All Jan →

Other small models

All small models →