EM

Emerhyst 20B Requantized

EmerhystGGUF by sandmanbuzzUpdated 2025-05-20
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant14.2 GB
Quick answer

Emerhyst 20B Requantized needs about 27.3 GB of memory at Q6_K (a 16.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 14.2 GB (Q5_K_M) to 40.0 GB.

Emerhyst 20B Requantized is a 20B-parameter Emerhyst model in GGUF format, quantized by sandmanbuzz. Its trained context length is 4K tokens. The repository has 3 quant files, from 14.2 GB (Q5_K_M) to 40.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M14.2 GB 19.9 GB
Too big Get file →
Q6_K16.4 GB 22.1 GB
Too big Get file →
—40.0 GB 45.7 GB
Too big Get file →

What GPU do you need for Emerhyst 20B Requantized?

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: the best quant that fits is Q6_K (16.4 GB file, about 27.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (16.4 GB file, about 27.3 GB in use).

Which Emerhyst 20B Requantized quant should you choose?

Q6_K (16.4 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K_M at 14.2 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters20B
Layers62
Trained context4,096 tokens
KV cache (fp16)1240 KB per token

Source

Quantized bysandmanbuzz
FamilyEmerhyst
Licenseother
Downloads (HF)37
Last updated2025-05-20

Frequently asked questions about Emerhyst 20B Requantized

How much VRAM does Emerhyst 20B Requantized need?

About 27.3 GB at Q6_K with an 8K context window. That is the 16.4 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 Emerhyst 20B Requantized on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Emerhyst 20B Requantized GGUF?

It depends on the quant: Q5_K_M is 14.2 GB, Q6_K is 16.4 GB, file is 40.0 GB.

What context length does Emerhyst 20B Requantized support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 10.4 GB at 8K and 5.2 GB at 4K.

Where can I download Emerhyst 20B Requantized GGUF?

The files are on Hugging Face in the sandmanbuzz/Emerhyst-20B-Requantized-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 Emerhyst 20B Requantized 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 Emerhyst-20B

Similar models

Browse all →

More from sandmanbuzz

All by sandmanbuzz →

More Emerhyst models

All Emerhyst →

Other medium models

All medium models →