FO

Forgotten Safeword 36B 4.1

ForgottenGGUF by ReadyArtUpdated 2026-03-27
Download on Hugging Face
Parameters36.9B
Context32K
Layers64
Architecturellama
Smallest quant40.5 GB
Quick answer

Forgotten Safeword 36B 4.1 needs about 43.1 GB of memory at Q8_0 (a 40.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Forgotten Safeword 36B 4.1 is a 36.9B-parameter Forgotten model in GGUF format, quantized by ReadyArt. Its trained context length is 32K tokens. The repository has 1 quant file, from 40.5 GB (Q8_0) to 40.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_040.5 GB 43.1 GB
Too big Get file →

What GPU do you need for Forgotten Safeword 36B 4.1?

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: the best quant that fits is Q8_0 (40.5 GB file, about 43.1 GB in use).

Which Forgotten Safeword 36B 4.1 quant should you choose?

Q8_0 (40.5 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters36.9B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized byReadyArt
FamilyForgotten
Licenseapache-2.0
Downloads (HF)95
Last updated2026-03-27

Frequently asked questions about Forgotten Safeword 36B 4.1

How much VRAM does Forgotten Safeword 36B 4.1 need?

About 43.1 GB at Q8_0 with an 8K context window. That is the 40.5 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 Forgotten Safeword 36B 4.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 43.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Forgotten Safeword 36B 4.1 GGUF?

It depends on the quant: Q8_0 is 40.5 GB.

What context length does Forgotten Safeword 36B 4.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Forgotten Safeword 36B 4.1 GGUF?

The files are on Hugging Face in the ReadyArt/Forgotten-Safeword-36B-4.1-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 Forgotten Safeword 36B 4.1 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.

Other GGUFs of Forgotten-Safeword-36B-4.1

Similar models

Browse all →

More from ReadyArt

All by ReadyArt →

More Forgotten models

All Forgotten →

Other large models

All large models →