MI

Mistral 7B Erebus v3

MistralGGUF by KoboldAIUpdated 2024-01-13
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.1 GB
Quick answer

Mistral 7B Erebus v3 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 3.1 GB (Q2_K) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mistral 7B Erebus v3 – a 7.24B parameter adult content co‑writing model

Mistral 7B Erebus v3 is a 7.24B parameter model trained on eight adult‑theme datasets. It is released under the apache-2.0 license and is intended for use with Koboldcpp and the KoboldAI Lite interface. The model is not suitable for minors.

Good at

  • Co‑writing adult themed stories
  • Large context handling up to 32768 tokens
  • Fine‑tuned for adult content generation

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Not suitable for minors

Best for

  • Adult content writers
  • Creative fiction authors
  • KoboldAI co‑writing sessions

Who it’s for. This model is aimed at users who need a specialized adult content generation tool and are comfortable with the model’s explicit nature. It is best used within the KoboldAI Lite interface in Story Mode.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.7 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q4_14.6 GB 6.1 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q5_15.4 GB 7.0 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →
F1614.5 GB 16.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (est. 5.9 GB) or Q5_K_M (est. 6.7 GB). For 12 GB VRAM, Q6_K (est. 7.5 GB) or Q8_0 (est. 9.3 GB) are suitable. Larger VRAM allows use of F16 (est. 16.1 GB).

What GPU do you need for Mistral 7B 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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which Mistral 7B Erebus v3 quant should you choose?

Q4_K_M is the usual starting point for Mistral 7B Erebus v3: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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 3.1 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byKoboldAI
FamilyMistral
Licenseapache-2.0
Downloads (HF)647
Last updated2024-01-13

Frequently asked questions about Mistral 7B Erebus v3

How much VRAM does Mistral 7B Erebus v3 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Mistral 7B Erebus v3 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mistral 7B Erebus v3 GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.2 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_0 is 4.1 GB, Q4_K_S is 4.1 GB and 9 more.

What context length does Mistral 7B Erebus v3 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Mistral 7B Erebus v3 GGUF?

The files are on Hugging Face in the KoboldAI/Mistral-7B-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 Mistral 7B Erebus v3 use?

Hugging Face lists the license as apache-2.0. 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 Mistral 7B Erebus v3 on 8 GB VRAM?

Yes, the Q4_K_M quant uses approximately 5.9 GB of VRAM at 8k context, which fits within an 8 GB budget.

Does this model support vision?

No, the model has no vision capabilities.

Is this model safe for all audiences?

No, the model outputs X-rated content and is not suitable for minors.

Similar models

Browse all →

More from KoboldAI

All by KoboldAI →

More Mistral models

All Mistral →

Other small models

All small models →