NO

Nocturne 4x22b

NocturneGGUF by fizzaclesUpdated 2026-06-10
Download on Hugging Face
Parameters84B
Context128K
Layers40
Architecturellama
Smallest quant50.9 GB
Quick answer

Nocturne 4x22b needs about 52.7 GB of memory at Q4_K_M (a 50.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 50.9 GB (Q4_K_M) to 168.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Nocturne 4x22b is a 84B-parameter Nocturne model in GGUF format, quantized by fizzacles. Its trained context length is 128K tokens. The repository has 2 quant files, from 50.9 GB (Q4_K_M) to 168.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M50.9 GB 52.7 GB
Too big Get file →
BF16168.0 GB 169.8 GB
Too big Get file →

What GPU do you need for Nocturne 4x22b?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Nocturne 4x22b quant should you choose?

Q4_K_M is the usual starting point for Nocturne 4x22b: it balances file size and quality well. Here it is a 50.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters84B (approximate, mixture of experts)
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byfizzacles
FamilyNocturne
Licensemit
Downloads (HF)14
Last updated2026-06-10

Frequently asked questions about Nocturne 4x22b

How much VRAM does Nocturne 4x22b need?

About 52.7 GB at Q4_K_M with an 8K context window. That is the 50.9 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 Nocturne 4x22b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 52.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nocturne 4x22b GGUF?

It depends on the quant: Q4_K_M is 50.9 GB, BF16 is 168.0 GB.

What context length does Nocturne 4x22b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Nocturne 4x22b GGUF?

The files are on Hugging Face in the fizzacles/Nocturne_4x22b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Nocturne 4x22b use?

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

Similar models

Browse all →

More from fizzacles

All by fizzacles →

More Nocturne models

All Nocturne →

Other large models

All large models →