Gemma 4 12B It Heretic_Decensored 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 14 quants, from 4.8 GB (Q2_K) to 23.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Gemma 4 12B It Heretic_Decensored – a reasoning‑capable model with reduced refusal behavior
Gemma 4 12B It Heretic_Decensored is built on google/gemma-4-12B-it and modified with the Heretic abliteration toolkit. It preserves instruction‑following and multi‑step reasoning while minimizing internal refusal tendencies. The model is released under apache‑2.0 for research use.
Good at
- Reasoning and multi‑step problem solving
- Instruction following
- Local inference on 12B scale models
Limits
- May generate unrestricted or sensitive content
- No vision support beyond detection
- Requires research‑level responsibility
Best for
- Alignment research and refusal‑behavior studies
- Benchmarking reasoning capabilities
- Red teaming experiments
Who it’s for. Researchers and developers focused on alignment, safety, and model behavior analysis. The model is intended for local inference in controlled environments and should be used with caution due to its reduced refusal mechanisms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 18.9 GB | Too big | Get file → | |
| Q3_K_M | 6.1 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_L | 6.6 GB | 20.0 GB | Too big | Get file → | |
| Q4_0 | 7.0 GB | 20.4 GB | Too big | Get file → | |
| Q4_K_S | 7.0 GB | 20.4 GB | Too big | Get file → | |
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q5_0 | 8.3 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 23.2 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → | |
| BF16 | 23.8 GB | 37.2 GB | Too big | Get file → | |
| F16 | 23.8 GB | 37.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (7.38 GB file, ~20.8 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (8.55 GB file, ~21.9 GB memory). For 16 GB VRAM, Q6_K (9.79 GB file, ~23.2 GB memory). Memory estimates are approximate.
What GPU do you need for Gemma 4 12B It Heretic_Decensored?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (23.8 GB file, about 37.2 GB in use).
Which Gemma 4 12B It Heretic_Decensored quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 12B It Heretic_Decensored: it balances file size and quality well. Here it is a 7.4 GB file.
The Q8_0 file is 12.7 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 Q2_K at 4.8 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
Source
Frequently asked questions about Gemma 4 12B It Heretic_Decensored
How much VRAM does Gemma 4 12B It Heretic_Decensored 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 Gemma 4 12B It Heretic_Decensored on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 12B It Heretic_Decensored GGUF?
It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.1 GB, Q3_K_L is 6.6 GB, Q4_0 is 7.0 GB, Q4_K_S is 7.0 GB and 8 more.
What context length does Gemma 4 12B It Heretic_Decensored 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 Gemma 4 12B It Heretic_Decensored GGUF?
The files are on Hugging Face in the prithivMLmods/gemma-4-12B-it-heretic_decensored-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 Gemma 4 12B It Heretic_Decensored 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 Gemma 4 12B It Heretic_Decensored on 8 GB VRAM?
Yes, using the Q4_K_M quantized file which requires about 20.8 GB of VRAM at 8k context, so 8 GB VRAM is insufficient for full inference.
Does this model support vision tasks?
No, the model does not include vision capabilities despite detecting vision ability.
What license applies to this model?
The model is released under the apache‑2.0 license.