JA

Jan-v1-4B

JanGGUF by janhqUpdated 2025-08-13
Download on Hugging Face
Parameters4B
Context256K
Layers36
Architectureqwen3
Smallest quant2.5 GB
Quick answer

Jan-v1-4B needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.5 GB (Q4_K_M) to 4.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Jan-v1-4B – 4B‑parameter Qwen3 agentic model

Jan-v1-4B is a 4B‑parameter Qwen3 model focused on agentic reasoning and problem‑solving. It is the first release in the Jan family and achieves 91.1% SimpleQA accuracy. The model is released under Apache‑2.0.

Good at

  • Agentic reasoning
  • Tool utilization
  • Complex problem solving

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • No explicit language support listed

Best for

  • Building agentic chatbots
  • Tool‑integrated assistants
  • Complex reasoning tasks

Who it’s for. Developers building agentic applications who need a lightweight 4B model. The model is suitable for local deployment with llama.cpp or vLLM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
Q5_K_M2.9 GB 4.6 GB
Fits Get file →
Q6_K3.3 GB 5.0 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →

For 8‑GB VRAM use Q4_K_M (file size 2.5 GB, estimated 4.2 GB memory). For 12‑GB VRAM use Q5_K_M (2.89 GB, 4.6 GB memory). Larger VRAM allows Q6_K or Q8_0 for higher precision.

What GPU do you need for Jan-v1-4B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).

Which Jan-v1-4B quant should you choose?

Q4_K_M is the usual starting point for Jan-v1-4B: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byjanhq
FamilyJan
Base modeljanhq/Jan-v1-4B
Licenseapache-2.0
Downloads (HF)4,036
Last updated2025-08-13

Frequently asked questions about Jan-v1-4B

How much VRAM does Jan-v1-4B need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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-v1-4B on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Jan-v1-4B GGUF?

It depends on the quant: Q4_K_M is 2.5 GB, Q5_K_M is 2.9 GB, Q6_K is 3.3 GB, Q8_0 is 4.3 GB.

What context length does Jan-v1-4B 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-v1-4B GGUF?

The files are on Hugging Face in the janhq/Jan-v1-4B-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-v1-4B 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-v1-4B on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 4.2 GB of VRAM at 8‑k context, which fits within 8 GB.

Does Jan-v1-4B support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of Jan-v1-4B

Similar models

Browse all →

More from janhq

All by janhq →

More Jan models

All Jan →

Other small models

All small models →