AM

Undi95 U Amethyst 20B

AmethystGGUF by tensorblockUpdated 2026-01-27
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant7.4 GB
Quick answer

Undi95 U Amethyst 20B needs about 18.3 GB of memory at Q2_K (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU.

Undi95 U Amethyst 20B is a 20B-parameter Amethyst model in GGUF format, quantized by tensorblock. Its trained context length is 4K tokens. The repository has 1 quant file, from 7.4 GB (Q2_K) to 7.4 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.4 GB 13.1 GB
Too big Get file →

What GPU do you need for Undi95 U Amethyst 20B?

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: the best quant that fits is Q2_K (7.4 GB file, about 18.3 GB in use).

Which Undi95 U Amethyst 20B quant should you choose?

Q2_K (7.4 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 bytensorblock
FamilyAmethyst
Downloads (HF)11
Last updated2026-01-27

Frequently asked questions about Undi95 U Amethyst 20B

How much VRAM does Undi95 U Amethyst 20B need?

About 18.3 GB at Q2_K with an 8K context window. That is the 7.4 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 Undi95 U Amethyst 20B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Undi95 U Amethyst 20B GGUF?

It depends on the quant: Q2_K is 7.4 GB.

What context length does Undi95 U Amethyst 20B 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 Undi95 U Amethyst 20B GGUF?

The files are on Hugging Face in the tensorblock/Undi95_U-Amethyst-20B-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 Undi95 U Amethyst 20B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 U-Amethyst-20B

Similar models

Browse all →

More from tensorblock

All by tensorblock →

More Amethyst models

All Amethyst →

Other medium models

All medium models →