ST

G4 Starry Ocean 12B Heretic

StarryGGUF by mradermacherUpdated 2026-07-10
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant0.0 GB
Quick answer

G4 Starry Ocean 12B Heretic needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.0 GB to 9.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

G4 Starry Ocean 12B Heretic – a 12B gemma4 model for roleplay and creative writing

G4 Starry Ocean 12B Heretic is a 11.9B parameter gemma4 model. It supports 262144 context tokens and is licensed under apache-2.0. The model is optimized for roleplay and long‑form storytelling.

Good at

  • Roleplay with emotion
  • Long‑form narrative
  • Creative atmospheric fiction

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • License requires apache-2.0 compliance

Best for

  • Interactive roleplay sessions
  • Writing long stories
  • Creative fiction generation

Who it’s for. Developers and writers who need a large language model for roleplay or creative writing. The model is suitable for local deployment with sufficient VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 13.4 GB
Too big Get file →
IQ1_S3.0 GB 16.4 GB
Too big Get file →
IQ1_M3.2 GB 16.6 GB
Too big Get file →
IQ2_XXS3.6 GB 17.0 GB
Too big Get file →
IQ2_XS3.9 GB 17.3 GB
Too big Get file →
IQ2_S4.1 GB 17.5 GB
Too big Get file →
IQ2_M4.4 GB 17.8 GB
Too big Get file →
Q2_K_S4.5 GB 17.9 GB
Too big Get file →
Q2_K4.8 GB 18.2 GB
Too big Get file →
IQ3_XXS4.8 GB 18.2 GB
Too big Get file →
IQ3_XS5.3 GB 18.7 GB
Too big Get file →
IQ3_S5.5 GB 18.9 GB
Too big Get file →
Q3_K_S5.5 GB 18.9 GB
Too big Get file →
IQ3_M5.7 GB 19.1 GB
Too big Get file →
Q3_K_M6.1 GB 19.5 GB
Too big Get file →
Q3_K_L6.6 GB 20.0 GB
Too big Get file →
IQ4_XS6.6 GB 20.0 GB
Too big Get file →
IQ4_NL7.0 GB 20.4 GB
Too big Get file →
Q4_07.0 GB 20.4 GB
Too big Get file →
Q4_K_S7.0 GB 20.4 GB
Too big Get file →
Q4_K_M7.4 GB 20.8 GB
Too big Get file →
Q4_17.7 GB 21.0 GB
Too big Get file →
Q5_K_S8.3 GB 21.7 GB
Too big Get file →
Q5_K_M8.5 GB 21.9 GB
Too big Get file →
Q6_K9.8 GB 23.2 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (file size 2.98 GB, memory 16.4 GB at 8k context). For 12‑GB VRAM, IQ2_S (4.08 GB, 17.5 GB). For 16‑GB VRAM, Q4_K_M (7.38 GB, 20.8 GB). Memory estimates are approximate.

What GPU do you need for G4 Starry Ocean 12B Heretic?

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 the main file (0.0 GB file, about 13.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).

Which G4 Starry Ocean 12B Heretic quant should you choose?

Q4_K_M is the usual starting point for G4 Starry Ocean 12B Heretic: it balances file size and quality well. Here it is a 7.4 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters11.9B
Layers48
Trained context262,144 tokens
KV cache (fp16)1536 KB per token

Source

Quantized bymradermacher
FamilyStarry
Licenseapache-2.0
Downloads (HF)4,049
Last updated2026-07-10

Frequently asked questions about G4 Starry Ocean 12B Heretic

How much VRAM does G4 Starry Ocean 12B Heretic need?

About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 G4 Starry Ocean 12B Heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of G4 Starry Ocean 12B Heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.1 GB and 19 more.

What context length does G4 Starry Ocean 12B Heretic support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.

Where can I download G4 Starry Ocean 12B Heretic GGUF?

The files are on Hugging Face in the mradermacher/G4-Starry-Ocean-12B-heretic-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 G4 Starry Ocean 12B Heretic 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 G4 Starry Ocean 12B Heretic on 8 GB VRAM?

Use the IQ1_S quant. It requires about 16.4 GB of VRAM at 8k context, which is beyond 8 GB, so it is not feasible on 8 GB VRAM.

Does this model support vision tasks?

No, this model does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of G4-Starry-Ocean-12B-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Starry models

All Starry →

Other medium models

All medium models →