JA

Jan-v3-4b-base-instruct

JanGGUF by janhqUpdated 2026-01-28
Download on Hugging Face
Parameters4.4B
Context256K
Layers36
Architectureqwen3
Smallest quant2.1 GB
Quick answer

Jan-v3-4b-base-instruct needs about 4.4 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 2.1 GB (Q3_K_S) to 8.8 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Jan-v3-4B-base-instruct – a 4.4B parameter Qwen3-based instruction model

Jan-v3-4B-base-instruct is a 4.4B parameter model distilled from a larger teacher. It supports a native context length of 262,144 tokens and is designed for instruction following and lightweight coding assistance. The model is open‑source under the Apache‑2.0 license.

Good at

  • Instruction following
  • Lightweight coding assistance
  • Large native context

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No mixture of experts

Best for

  • Fine‑tuning small instruction models
  • Chatbot back‑end with long context
  • Code generation tasks

Who it’s for. Developers and researchers who need a compact, ownable base for downstream fine‑tuning. The model is suitable for building chat or coding assistants that require a large context window without heavy GPU memory usage.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S2.1 GB 3.8 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 →
Q4_02.6 GB 4.3 GB
Fits Get file →
Q4_K_S2.6 GB 4.3 GB
Fits Get file →
Q4_K_M2.7 GB 4.4 GB
Fits Get file →
Q4_12.8 GB 4.5 GB
Fits Get file →
Q4_K_XL3.0 GB 4.7 GB
Fits Get file →
Q5_03.1 GB 4.8 GB
Fits Get file →
Q5_K_S3.1 GB 4.8 GB
Fits Get file →
Q5_K_M3.2 GB 4.9 GB
Fits Get file →
Q5_13.3 GB 5.1 GB
Fits Get file →
Q6_K3.6 GB 5.3 GB
Fits Get file →
Q8_04.7 GB 6.4 GB
Fits Get file →
—8.8 GB 10.5 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 2.72 GB, estimated 4.4 GB memory). For 12 GB VRAM use Q5_K_M (file size 3.16 GB, estimated 4.9 GB memory). For 16 GB VRAM use Q6_K (file size 3.63 GB, estimated 5.3 GB memory).

What GPU do you need for Jan-v3-4b-base-instruct?

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 (3.6 GB file, about 5.3 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 the main file (8.8 GB file, about 10.5 GB in use).

Which Jan-v3-4b-base-instruct quant should you choose?

Q4_K_M is the usual starting point for Jan-v3-4b-base-instruct: it balances file size and quality well. Here it is a 2.7 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 Q3_K_S at 2.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.4B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byjanhq
FamilyJan
Licenseapache-2.0
Downloads (HF)3,546
Last updated2026-01-28

Frequently asked questions about Jan-v3-4b-base-instruct

How much VRAM does Jan-v3-4b-base-instruct need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.7 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-v3-4b-base-instruct 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-v3-4b-base-instruct GGUF?

It depends on the quant: Q3_K_S is 2.1 GB, Q3_K_M is 2.2 GB, Q3_K_L is 2.4 GB, Q4_0 is 2.6 GB, Q4_K_S is 2.6 GB, Q4_K_M is 2.7 GB and 9 more.

What context length does Jan-v3-4b-base-instruct 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-v3-4b-base-instruct GGUF?

The files are on Hugging Face in the janhq/Jan-v3-4B-base-instruct-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-v3-4b-base-instruct 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-v3-4B-base-instruct on 8 GB VRAM?

Yes, using Q4_K_M quantization which requires about 4.4 GB of VRAM at 8k context.

Does this model support image inputs?

No, Jan-v3-4B-base-instruct has no vision capability.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Jan-v3-4B-base-instruct

Similar models

Browse all →

More from janhq

All by janhq →

More Jan models

All Jan →

Other small models

All small models →