RE

Refusals

RefusalsGGUF by lyraaaaUpdated 2026-02-14
Download on Hugging Face
Parameters6.12B
Context128K
Layers56
Architectureafmoe
Smallest quant6.5 GB
Quick answer

Refusals needs about 7.5 GB of memory at Q8_0 (a 6.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Refusals is a 6.12B-parameter Refusals model in GGUF format, quantized by lyraaaa. Its trained context length is 128K tokens. The repository has 1 quant file, from 6.5 GB (Q8_0) to 6.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_06.5 GB 7.5 GB
Tight Get file →

What GPU do you need for Refusals?

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 Q8_0 (6.5 GB file, about 7.5 GB in use).

Which Refusals quant should you choose?

Q8_0 (6.5 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

Architectureafmoe
Parameters6.12B (approximate, mixture of experts)
Layers56
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized bylyraaaa
FamilyRefusals
Downloads (HF)37
Last updated2026-02-14

Frequently asked questions about Refusals

How much VRAM does Refusals need?

About 7.5 GB at Q8_0 with an 8K context window. That is the 6.5 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 Refusals on an 8 GB GPU?

Yes, with Q8_0: the 6.5 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Refusals GGUF?

It depends on the quant: Q8_0 is 6.5 GB.

What context length does Refusals support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Refusals GGUF?

The files are on Hugging Face in the lyraaaa/refusals_q8_0_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 lyraaaa

All by lyraaaa →

Other small models

All small models →