AT

Athene 70B

AtheneGGUF by mradermacherUpdated 2024-09-09
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

Athene 70B needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 20 quants, from 15.3 GB (IQ1_S) to 49.9 GB (Q5_K_M).

Athene 70B – a 70.6B parameter Llama chat model

Athene 70B is a 70.6B parameter Llama model fine‑tuned from Llama‑3‑70B‑Instruct. It is available in multiple GGUF quantizations and supports a 8192 token context window. The model is released under a Nexusflow Research License.

Good at

  • Large context chat
  • High‑quality instruction following
  • LLM inference with GGUF

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License not public domain

Best for

  • Chatbot development
  • Research prototyping
  • Fine‑tuning experiments

Who it’s for. Developers and researchers who need a large Llama‑3 based chat model with open‑weights and multiple quant options. The model is suitable for those who can manage the memory requirements and comply with the Nexusflow license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S15.3 GB 18.5 GB
Too big Get file →
IQ1_M16.8 GB 19.9 GB
Too big Get file →
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_S22.2 GB 25.4 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XXS27.5 GB 30.7 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ3_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
Q4_040.1 GB 43.3 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 15.34 GB, estimated 18.5 GB memory). For 12 GB VRAM, IQ2_XS (21.14 GB, 24.3 GB memory) or Q2_K (26.38 GB, 29.6 GB memory) are suitable. For 24 GB VRAM, Q4_K_M (42.52 GB, 45.7 GB memory) or Q5_K_M (49.95 GB, 53.1 GB memory) provide higher quality.

What GPU do you need for Athene 70B?

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 IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which Athene 70B quant should you choose?

Q4_K_M is the usual starting point for Athene 70B: it balances file size and quality well. Here it is a 42.5 GB file.

If memory is tight, the smallest file is IQ1_S at 15.3 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
Parameters70.6B
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyAthene
Licenseother
Downloads (HF)1,924
Last updated2024-09-09

Frequently asked questions about Athene 70B

How much VRAM does Athene 70B need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Athene 70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Athene 70B GGUF?

It depends on the quant: IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB, IQ2_M is 24.1 GB and 14 more.

What context length does Athene 70B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download Athene 70B GGUF?

The files are on Hugging Face in the mradermacher/Athene-70B-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 Athene 70B 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.

Can I run Athene 70B on 8 GB VRAM?

Use the IQ1_S quant, which requires about 18.5 GB of VRAM at 8k context. 8 GB VRAM is insufficient.

Does Athene 70B support vision tasks?

No, the model has no vision capabilities.

What license applies to Athene 70B?

The model is released under a Nexusflow Research License.

Other GGUFs of Athene-70B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Athene models

All Athene →

Other large models

All large models →