GE

Erebus RP 12B Instruct 2608 v1

GemmaGGUF by IndexnusrefatherUpdated 2026-08-17
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant6.0 GB
Quick answer

Erebus RP 12B Instruct 2608 v1 needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 6.0 GB (Q3_K_M) to 23.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Erebus RP 12B Instruct 2608 v1 – a Gemma 3 12B fine‑tuned for roleplay and creative writing

Erebus RP 12B Instruct 2608 v1 is a 11.8 billion‑parameter Gemma 3 model fine‑tuned on curated chat logs. It focuses on roleplay and creative writing, offering longer messages and better story tracking. The model is available in multiple GGUF quantizations.

Good at

  • Roleplay and creative storytelling
  • Long‑form dialogue
  • Adaptive writing style

Limits

  • No vision support
  • License is gemma
  • Context limited to 131072 tokens

Best for

  • Chatbot roleplay sessions
  • Creative writing assistants
  • Story generation tools

Who it’s for. Developers and hobbyists building role‑play chatbots or creative writing assistants who need a lightweight yet expressive model. The model is suitable for projects that can run GGUF files on local hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M6.0 GB 9.7 GB
Too big Get file →
Q4_K_M7.3 GB 11.0 GB
Too big Get file →
Q5_K_M8.4 GB 12.2 GB
Too big Get file →
Q6_K9.7 GB 13.4 GB
Too big Get file →
Q8_012.5 GB 16.2 GB
Too big Get file →
BF1623.5 GB 27.3 GB
Too big Get file →

For 8 GB VRAM, Q4_K_M (file size 7.3 GB, estimated 11 GB memory) is recommended. With 12 GB VRAM, Q5_K_M (8.45 GB, 12.2 GB memory) offers higher quality. If more VRAM is available, Q6_K (9.66 GB, 13.4 GB memory) provides near‑lossless performance.

What GPU do you need for Erebus RP 12B Instruct 2608 v1?

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: the best quant that fits is Q4_K_M (7.3 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (23.5 GB file, about 27.3 GB in use).

Which Erebus RP 12B Instruct 2608 v1 quant should you choose?

Q4_K_M is the usual starting point for Erebus RP 12B Instruct 2608 v1: it balances file size and quality well. Here it is a 7.3 GB file.

The Q8_0 file is 12.5 GB, about 1.7 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 Q3_K_M at 6.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters11.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byIndexnusrefather
FamilyGemma
Licensegemma
Downloads (HF)1,094
Last updated2026-08-17

Frequently asked questions about Erebus RP 12B Instruct 2608 v1

How much VRAM does Erebus RP 12B Instruct 2608 v1 need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 Erebus RP 12B Instruct 2608 v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Erebus RP 12B Instruct 2608 v1 GGUF?

It depends on the quant: Q3_K_M is 6.0 GB, Q4_K_M is 7.3 GB, Q5_K_M is 8.4 GB, Q6_K is 9.7 GB, Q8_0 is 12.5 GB, BF16 is 23.5 GB.

What context length does Erebus RP 12B Instruct 2608 v1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Erebus RP 12B Instruct 2608 v1 GGUF?

The files are on Hugging Face in the Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-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 Erebus RP 12B Instruct 2608 v1 use?

Hugging Face lists the license as gemma. 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 Erebus RP 12B Instruct 2608 v1 on 8 GB VRAM?

Yes, use the Q4_K_M quantization which requires about 11 GB of VRAM at 8k context.

Does this model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is licensed under the gemma license.

Other GGUFs of gemma-3-12b-it

Similar models

Browse all →

More from Indexnusrefather

All by Indexnusrefather →

More Gemma models

All Gemma →

Other medium models

All medium models →