JU

Juno N Coder 25B A3B

JunoGGUF by mradermacherUpdated 2026-08-24
Download on Hugging Face
Parameters25.2B
Context1024K
Layers53
Architecturenemotron_h_moe
Smallest quant0.0 GB
Quick answer

Juno N Coder 25B A3B needs about 27.1 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 15 quants, from 0.0 GB to 26.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.

Juno N Coder 25B A3B is a 25.2B-parameter Juno model in GGUF format, quantized by mradermacher. Its trained context length is 1024K tokens. The repository has 15 quant files, from 0.0 GB to 26.8 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 7.7 GB
Tight Get file →
Q2_K14.3 GB 22.0 GB
Too big Get file →
IQ3_S14.4 GB 22.0 GB
Too big Get file →
Q3_K_S14.4 GB 22.0 GB
Too big Get file →
IQ4_XS14.4 GB 22.0 GB
Too big Get file →
Q4_014.5 GB 22.1 GB
Too big Get file →
IQ3_M14.5 GB 22.1 GB
Too big Get file →
Q3_K_M15.9 GB 23.5 GB
Too big Get file →
Q4_116.0 GB 23.6 GB
Too big Get file →
Q3_K_L16.6 GB 24.2 GB
Too big Get file →
Q4_K_S17.5 GB 25.2 GB
Too big Get file →
Q5_K_S19.1 GB 26.7 GB
Too big Get file →
Q4_K_M19.5 GB 27.1 GB
Too big Get file →
Q5_K_M20.7 GB 28.4 GB
Too big Get file →
Q6_K26.8 GB 34.4 GB
Too big Get file →

What GPU do you need for Juno N Coder 25B A3B?

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: the best quant that fits is the main file (0.0 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 7.7 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 7.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (16.0 GB file, about 23.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (20.7 GB file, about 28.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (26.8 GB file, about 34.4 GB in use).

Which Juno N Coder 25B A3B quant should you choose?

Q4_K_M is the usual starting point for Juno N Coder 25B A3B: it balances file size and quality well. Here it is a 19.5 GB file.

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

Architecturenemotron_h_moe
Parameters25.2B (approximate, mixture of experts)
Active parameters3B
Layers53
Trained context1,048,576 tokens
KV cache (fp16)848 KB per token

Source

Quantized bymradermacher
FamilyJuno
Licenseother
Downloads (HF)237
Last updated2026-08-24

Frequently asked questions about Juno N Coder 25B A3B

How much VRAM does Juno N Coder 25B A3B need?

About 27.1 GB at Q4_K_M with an 8K context window. That is the 19.5 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 Juno N Coder 25B A3B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Juno N Coder 25B A3B GGUF?

It depends on the quant: file is 0.0 GB, Q2_K is 14.3 GB, IQ3_S is 14.4 GB, Q3_K_S is 14.4 GB, IQ4_XS is 14.4 GB, Q4_0 is 14.5 GB and 9 more.

What context length does Juno N Coder 25B A3B 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 7.1 GB at 8K and 28.5 GB at 32K.

Where can I download Juno N Coder 25B A3B GGUF?

The files are on Hugging Face in the mradermacher/Juno-N-Coder-25B-A3B-i1-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 Juno N Coder 25B A3B use?

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

Other GGUFs of Juno-N-Coder-25B-A3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Juno models

All Juno →

Other medium models

All medium models →