AM

Amethyst 13B

AmethystGGUF by TheBlokeUpdated 2023-11-01
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

Amethyst 13B needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 5.4 GB (Q2_K) to 13.8 GB (Q8_0).

Amethyst 13B – a 13‑billion‑parameter Llama model in GGUF format

Amethyst 13B is a 13‑billion‑parameter Llama model quantised into GGUF files. It supports a 4096‑token context window and is released under a CC‑BY‑NC‑4.0 license. The model was created by TheBloke from the original Amethyst 13B.

Good at

  • Large context reasoning
  • Multilingual text generation
  • Fine‑tuning with LoRA

Limits

  • Requires at least 12.6 GB VRAM for Q2_K
  • No vision or audio capabilities
  • CC‑BY‑NC‑4.0 license limits commercial use

Best for

  • Chatbots needing long context
  • Research prototypes with GPU resources
  • Educational demos of Llama architecture

Who it’s for. Developers and researchers who need a sizeable Llama model with a 4096‑token context window and who can work within a CC‑BY‑NC‑4.0 license. The model is suitable for those who have access to GPUs with at least 12 GB of VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 9.3 GB
Too big Get file →
Q3_K_S5.7 GB 9.5 GB
Too big Get file →
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.8 GB
Too big Get file →
Q4_07.4 GB 11.2 GB
Too big Get file →
Q4_K_S7.4 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →
Q5_09.0 GB 12.8 GB
Too big Get file →
Q5_K_S9.0 GB 12.8 GB
Too big Get file →
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →
Q8_013.8 GB 17.7 GB
Too big Get file →

For 12 GB VRAM, use Q2_K (5.43 GB file, 12.6 GB memory). If you have 14 GB VRAM, Q4_0 or Q4_K_S (7.37 GB file, 14.6 GB memory) are suitable. For 16 GB VRAM, Q5_K_M (9.23 GB file, 16.4 GB memory) provides a good balance of size and performance.

What GPU do you need for Amethyst 13B?

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 Q4_K_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which Amethyst 13B quant should you choose?

Q4_K_M is the usual starting point for Amethyst 13B: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 5.4 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
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyAmethyst
Downloads (HF)603
Last updated2023-11-01

Frequently asked questions about Amethyst 13B

How much VRAM does Amethyst 13B need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 Amethyst 13B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Amethyst 13B GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.4 GB and 6 more.

What context length does Amethyst 13B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download Amethyst 13B GGUF?

The files are on Hugging Face in the TheBloke/Amethyst-13B-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 Amethyst 13B 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 Amethyst 13B on 8 GB VRAM?

No. The smallest quantisation (Q2_K) requires 12.6 GB of VRAM at 8K context.

Is the model suitable for commercial applications?

No. The CC‑BY‑NC‑4.0 license prohibits commercial use without permission.

Does Amethyst 13B support vision or audio?

No. The model only handles text and has no vision or audio capabilities.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Amethyst models

All Amethyst →

Other medium models

All medium models →