LL

LLaMA2 13B Erebus v3

LlamaGGUF by KoboldAIUpdated 2024-01-13
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

LLaMA2 13B Erebus v3 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 15 quants, from 5.4 GB (Q2_K) to 26.0 GB (F16).

LLaMA2 13B Erebus v3 – a 13‑billion‑parameter adult‑content model

LLaMA2 13B Erebus v3 is a 13‑billion‑parameter Llama model trained on 2.3B tokens from eight adult‑theme datasets. It is designed for co‑writing in KoboldAI Lite and outputs X‑rated content. The model is not suitable for minors.

Good at

  • Co‑writing adult stories
  • High‑quality text generation
  • Customizable via KoboldAI

Limits

  • Requires 8‑k context for estimates
  • Strong NSFW bias
  • No vision support

Best for

  • Adult fiction writing
  • Interactive storytelling
  • Content moderation testing

Who it’s for. Developers and writers looking for a specialized adult‑content generation tool. The model is intended for use by adults only and should be handled with care.

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 →
Q4_18.2 GB 12.0 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 →
Q5_19.8 GB 13.6 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 →
F1626.0 GB 29.9 GB
Too big Get file →

For 8‑GB VRAM, use Q4_0 (7.37 GB file, 14.6 GB memory). For 12‑GB VRAM, Q5_0 (8.97 GB file, 16.2 GB memory) is suitable. For 16‑GB VRAM, Q6_K (10.68 GB file, 17.9 GB memory) provides higher quality.

What GPU do you need for LLaMA2 13B Erebus v3?

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_1 (8.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (26.0 GB file, about 33.2 GB in use).

Which LLaMA2 13B Erebus v3 quant should you choose?

Q4_K_M is the usual starting point for LLaMA2 13B Erebus v3: 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 byKoboldAI
FamilyLlama
Licensellama2
Downloads (HF)929
Last updated2024-01-13

Frequently asked questions about LLaMA2 13B Erebus v3

How much VRAM does LLaMA2 13B Erebus v3 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 LLaMA2 13B Erebus v3 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 LLaMA2 13B Erebus v3 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 9 more.

What context length does LLaMA2 13B Erebus v3 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 LLaMA2 13B Erebus v3 GGUF?

The files are on Hugging Face in the KoboldAI/LLaMA2-13B-Erebus-v3-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 LLaMA2 13B Erebus v3 use?

Hugging Face lists the license as llama2. 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 LLaMA2 13B Erebus v3 on 8 GB VRAM?

Use the Q4_0 quantized file; it requires about 14.6 GB of VRAM at 8‑k context, so 8 GB is insufficient.

Is this model safe for general use?

No. The model has a strong NSFW bias and is not suitable for minors.

What context length does it support?

It was trained on 4096 tokens and estimates are given for 8‑k context.

Similar models

Browse all →

More from KoboldAI

All by KoboldAI →

More Llama models

All Llama →

Other medium models

All medium models →