AT

Athena v2

AthenaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

Athena v2 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).

Athena v2 – 13B llama model in GGUF format

Athena v2 is a 13‑billion‑parameter llama model available in multiple GGUF quantisations. It was created by IkariDev and Undi95 and released under a cc‑by‑nc‑4.0 license. The model supports a 4096‑token context window and is trained in Alpaca format.

Good at

  • Alpaca‑style instruction following
  • General language tasks
  • Chat‑style interactions

Limits

  • No vision support
  • cc‑by‑nc‑4.0 license limits commercial use
  • Requires 8‑k context for memory estimates

Best for

  • Local chat applications
  • Story generation on GPU
  • Fine‑tuning for custom prompts

Who it’s for. Developers and researchers who need a 13B llama model for local inference. The model is suitable for those who can run GGUF files on llama.cpp or compatible libraries.

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 8‑GB VRAM use Q4_K_M (est. 15.1 GB memory). For 12‑GB VRAM use Q5_K_M (est. 16.4 GB). For 16‑GB VRAM use Q6_K (est. 17.9 GB). File sizes range from 5.43 GB (Q2_K) to 13.83 GB (Q8_0).

What GPU do you need for Athena v2?

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 Athena v2 quant should you choose?

Q4_K_M is the usual starting point for Athena v2: 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
FamilyAthena
Downloads (HF)2,694
Last updated2023-09-27

Frequently asked questions about Athena v2

How much VRAM does Athena v2 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 Athena v2 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 Athena v2 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 Athena v2 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 Athena v2 GGUF?

The files are on Hugging Face in the TheBloke/Athena-v2-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 Athena v2 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 Athena v2 on 8 GB VRAM?

Yes, using the Q4_K_M quantisation which requires approximately 15.1 GB of VRAM at 8‑k context.

Does Athena v2 support image inputs?

No, the model does not include vision capabilities.

Is Athena v2 free for commercial use?

No, it is licensed under cc‑by‑nc‑4.0, which prohibits commercial use without permission.

Other GGUFs of Athena-v2

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Athena models

All Athena →

Other medium models

All medium models →