JU

Jupiter N 4B

JupiterGGUF by mradermacherUpdated 2026-04-30
Download on Hugging Face
Parameters3.97B
Context1024K
Layers42
Architecturenemotron_h
Smallest quant2.2 GB
Quick answer

Jupiter N 4B needs about 10.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.2 GB (Q2_K) to 8.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 28.2 GB.

Jupiter N 4B is a 3.97B-parameter Jupiter model in GGUF format, quantized by mradermacher. Its trained context length is 1024K tokens. The repository has 12 quant files, from 2.2 GB (Q2_K) to 8.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.2 GB 9.8 GB
Too big Get file →
Q3_K_S2.3 GB 9.8 GB
Too big Get file →
Q3_K_M2.4 GB 9.9 GB
Too big Get file →
IQ4_XS2.4 GB 10.0 GB
Too big Get file →
Q3_K_L2.5 GB 10.0 GB
Too big Get file →
Q4_K_S2.8 GB 10.3 GB
Too big Get file →
Q4_K_M2.8 GB 10.4 GB
Too big Get file →
Q5_K_S3.0 GB 10.6 GB
Too big Get file →
Q5_K_M3.1 GB 10.6 GB
Too big Get file →
Q6_K3.9 GB 11.5 GB
Too big Get file →
Q8_04.2 GB 11.8 GB
Too big Get file →
F168.0 GB 15.5 GB
Too big Get file →

What GPU do you need for Jupiter N 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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (8.0 GB file, about 15.5 GB in use).

Which Jupiter N 4B quant should you choose?

Q4_K_M is the usual starting point for Jupiter N 4B: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 4.2 GB, about 1.5 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 Q2_K at 2.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h
Parameters3.97B
Layers42
Trained context1,048,576 tokens
KV cache (fp16)840 KB per token

Source

Quantized bymradermacher
FamilyJupiter
Downloads (HF)69
Last updated2026-04-30

Frequently asked questions about Jupiter N 4B

How much VRAM does Jupiter N 4B need?

About 10.4 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 Jupiter N 4B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Jupiter N 4B GGUF?

It depends on the quant: Q2_K is 2.2 GB, Q3_K_S is 2.3 GB, Q3_K_M is 2.4 GB, IQ4_XS is 2.4 GB, Q3_K_L is 2.5 GB, Q4_K_S is 2.8 GB and 6 more.

What context length does Jupiter N 4B support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.0 GB at 8K and 28.2 GB at 32K.

Where can I download Jupiter N 4B GGUF?

The files are on Hugging Face in the mradermacher/Jupiter-N-4B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Jupiter models

All Jupiter →

Other small models

All small models →