GE

Amoral Gemma3 12B

GemmaGGUF by bartowskiUpdated 2025-03-18
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant4.0 GB
Quick answer

Amoral Gemma3 12B 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 25 quants, from 4.0 GB (IQ2_S) to 23.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Amoral Gemma3 12B – neutral response LLM

Amoral Gemma3 12B is a 11.8 billion‑parameter model based on Gemma 3. It is optimized for unbiased, analytically neutral responses to sensitive queries. The model is released under Apache‑2.0 and supports a 131072‑token context window.

Good at

  • Neutral analysis of controversial topics
  • Bias benchmarking studies
  • Sensitive historical analysis

Limits

  • No vision support
  • Requires large VRAM for higher‑quality quants
  • No moral alignment mechanisms

Best for

  • Controversial topic analysis
  • Ethical philosophy simulations
  • Content moderation tool development

Who it’s for. Researchers and developers needing a neutral, fact‑centric LLM for sensitive content. It is suitable for academic studies, moderation tools, and simulations that require unbiased responses.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_S4.0 GB 7.7 GB
Tight Get file →
IQ2_M4.3 GB 8.0 GB
Too big Get file →
Q2_K4.8 GB 8.5 GB
Too big Get file →
IQ3_XXS4.8 GB 8.5 GB
Too big Get file →
Q2_K_L5.0 GB 8.7 GB
Too big Get file →
IQ3_XS5.2 GB 8.9 GB
Too big Get file →
Q3_K_S5.5 GB 9.2 GB
Too big Get file →
IQ3_M5.7 GB 9.4 GB
Too big Get file →
Q3_K_M6.0 GB 9.7 GB
Too big Get file →
Q3_K_L6.5 GB 10.2 GB
Too big Get file →
IQ4_XS6.6 GB 10.3 GB
Too big Get file →
Q3_K_XL6.7 GB 10.4 GB
Too big Get file →
IQ4_NL6.9 GB 10.6 GB
Too big Get file →
Q4_06.9 GB 10.6 GB
Too big Get file →
Q4_K_S6.9 GB 10.7 GB
Too big Get file →
Q4_K_M7.3 GB 11.0 GB
Too big Get file →
Q4_K_L7.5 GB 11.3 GB
Too big Get file →
Q4_17.6 GB 11.3 GB
Too big Get file →
Q5_K_S8.2 GB 12.0 GB
Too big Get file →
Q5_K_M8.4 GB 12.2 GB
Too big Get file →
Q5_K_L8.7 GB 12.4 GB
Too big Get file →
Q6_K9.7 GB 13.4 GB
Too big Get file →
Q6_K_L9.9 GB 13.6 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, use IQ2_S or IQ2_M. For 12 GB VRAM, Q3_K_S or Q3_K_M are suitable. For 16 GB VRAM, Q4_K_L or Q5_K_L provide higher quality while staying within memory limits. Memory estimates are approximate.

What GPU do you need for Amoral Gemma3 12B?

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: the best quant that fits is IQ2_M (4.3 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_S (8.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K_L (9.9 GB file, about 13.6 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 Amoral Gemma3 12B quant should you choose?

Q4_K_M is the usual starting point for Amoral Gemma3 12B: 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 IQ2_S at 4.0 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

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

Source

Quantized bybartowski
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,902
Last updated2025-03-18

Frequently asked questions about Amoral Gemma3 12B

How much VRAM does Amoral Gemma3 12B 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 Amoral Gemma3 12B on an 8 GB GPU?

Yes, with IQ2_M: the 4.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Amoral Gemma3 12B GGUF?

It depends on the quant: IQ2_S is 4.0 GB, IQ2_M is 4.3 GB, Q2_K is 4.8 GB, IQ3_XXS is 4.8 GB, Q2_K_L is 5.0 GB, IQ3_XS is 5.2 GB and 19 more.

What context length does Amoral Gemma3 12B 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 Amoral Gemma3 12B GGUF?

The files are on Hugging Face in the bartowski/soob3123_amoral-gemma3-12B-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 Amoral Gemma3 12B 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 Q4_K_L on 12 GB VRAM?

Q4_K_L requires about 11.3 GB at 8k context, so it fits within 12 GB VRAM with some headroom.

Does the model support image input?

No, the model has no vision capabilities.

Is the model free to use?

Yes, it is licensed under Apache‑2.0 and can be used freely for research and commercial projects.

Other GGUFs of amoral-gemma3-12B-v1

Similar models

Browse all →

More from bartowski

All by bartowski →

More Gemma models

All Gemma →

Other medium models

All medium models →