AM

U Amethyst 20B i1

AmethystGGUF by mradermacherUpdated 2024-09-09
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant4.4 GB
Quick answer

U Amethyst 20B i1 needs about 22.9 GB of memory at Q4_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 4.4 GB (IQ1_S) to 16.4 GB (Q6_K).

U Amethyst 20B i1 – a 20‑billion‑parameter llama model in GGUF format

U Amethyst 20B i1 is a 20‑billion‑parameter llama model quantized into multiple GGUF files. It supports a 4096‑token context window and is released under a cc‑by‑nc‑4.0 license. The model was assembled from several source models and includes LimaRP v3 settings.

Good at

  • Large context reasoning
  • High‑parameter language modeling
  • Customizable quantization

Limits

  • No vision support
  • License restricts commercial use
  • Requires 8‑k context for memory estimates

Best for

  • Research prototypes
  • Non‑commercial LLM demos
  • Fine‑tuning experiments

Who it’s for. Developers and researchers who need a large llama model for non‑commercial projects. The model is suitable for those who can manage the memory requirements and comply with the cc‑by‑nc‑4.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.4 GB 10.1 GB
Too big Get file →
IQ1_M4.8 GB 10.5 GB
Too big Get file →
IQ2_XXS5.4 GB 11.1 GB
Too big Get file →
IQ2_XS5.9 GB 11.6 GB
Too big Get file →
IQ2_S6.4 GB 12.1 GB
Too big Get file →
IQ2_M6.9 GB 12.6 GB
Too big Get file →
Q2_K7.4 GB 13.1 GB
Too big Get file →
IQ3_XXS7.6 GB 13.3 GB
Too big Get file →
IQ3_XS8.2 GB 13.9 GB
Too big Get file →
IQ3_S8.7 GB 14.4 GB
Too big Get file →
Q3_K_S8.7 GB 14.4 GB
Too big Get file →
IQ3_M9.2 GB 14.9 GB
Too big Get file →
Q3_K_M9.7 GB 15.4 GB
Too big Get file →
Q3_K_L10.6 GB 16.3 GB
Too big Get file →
IQ4_XS10.7 GB 16.4 GB
Too big Get file →
Q4_011.3 GB 17.0 GB
Too big Get file →
Q4_K_S11.4 GB 17.1 GB
Too big Get file →
Q4_K_M12.0 GB 17.7 GB
Too big Get file →
Q5_K_S13.8 GB 19.5 GB
Too big Get file →
Q5_K_M14.2 GB 19.9 GB
Too big Get file →
Q6_K16.4 GB 22.1 GB
Too big Get file →

For a 16‑GB VRAM system, the Q4_K_M quant (12.04 GB file, 22.9 GB memory at 8k context) is a good balance. If you have 8‑GB VRAM, consider the IQ1_S quant (4.39 GB file, 15.3 GB memory). For the lowest memory footprint, IQ1_S is recommended, but it uses the smallest file size.

What GPU do you need for U Amethyst 20B i1?

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: the best quant that fits is IQ1_M (4.8 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (12.0 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (16.4 GB file, about 27.3 GB in use).

Which U Amethyst 20B i1 quant should you choose?

Q4_K_M is the usual starting point for U Amethyst 20B i1: it balances file size and quality well. Here it is a 12.0 GB file.

If memory is tight, the smallest file is IQ1_S at 4.4 GB, with the quality trade-offs that come with fewer bits. 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 bymradermacher
FamilyAmethyst
Downloads (HF)727
Last updated2024-09-09

Frequently asked questions about U Amethyst 20B i1

How much VRAM does U Amethyst 20B i1 need?

About 22.9 GB at Q4_K_M with an 8K context window. That is the 12.0 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 U Amethyst 20B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of U Amethyst 20B i1 GGUF?

It depends on the quant: IQ1_S is 4.4 GB, IQ1_M is 4.8 GB, IQ2_XXS is 5.4 GB, IQ2_XS is 5.9 GB, IQ2_S is 6.4 GB, IQ2_M is 6.9 GB and 15 more.

What context length does U Amethyst 20B i1 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 U Amethyst 20B i1 GGUF?

The files are on Hugging Face in the mradermacher/U-Amethyst-20B-i1-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 U Amethyst 20B i1 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.

Can I run U Amethyst 20B i1 on 8 GB VRAM?

The smallest quant, IQ1_S, requires 15.3 GB memory at 8k context, so 8 GB VRAM is insufficient.

Is the model suitable for commercial use?

No, the cc‑by‑nc‑4.0 license prohibits commercial use.

Does the model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of U-Amethyst-20B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Amethyst models

All Amethyst →

Other medium models

All medium models →