Gemma 3 12b It Heretic v2 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 8 quants, from 6.0 GB (Q3_K_M) to 23.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Gemma 3 12B IT – Heretic v2, a lightweight, uncensored text encoder for video generation
Gemma 3 12B IT – Heretic v2 is an ablated version of Google’s Gemma 3 12B IT. It reduces refusals while preserving vision capabilities. The model is suitable for text‑to‑video pipelines and other multimodal tasks.
Good at
- Low‑refusal text encoding
- Vision‑enabled prompt enhancement
- Uncensored generation
Limits
- Large context size of 131072 tokens
- Requires 8‑k context memory estimates up to 27.3 GB
- No external vision training data provided
Best for
- Video generation with LTX‑2
- Multimodal prompt enhancement in ComfyUI
- Text encoding for Blackwell GPU workflows
Who it’s for. Developers building video generation models or multimodal pipelines who need a lightweight, uncensored text encoder with preserved vision support. The model is ideal for users with GPU memory constraints who prefer 4‑bit quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 6.0 GB | 9.7 GB | Too big | Get file → | |
| Q4_K_S | 6.9 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 11.0 GB | Too big | Get file → | |
| Q5_K_S | 8.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 12.2 GB | Too big | Get file → | |
| Q6_K | 9.7 GB | 13.4 GB | Too big | Get file → | |
| Q8_0 | 12.5 GB | 16.2 GB | Too big | Get file → | |
| F16 | 23.5 GB | 27.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_M (6.01 GB file, 9.7 GB memory). For 16 GB VRAM, Q4_K_S (6.94 GB file, 10.7 GB memory) or Q4_K_M (7.3 GB file, 11 GB memory). For 32 GB VRAM, Q6_K (9.66 GB file, 13.4 GB memory) or Q8_0 (12.51 GB file, 16.2 GB memory).
What GPU do you need for Gemma 3 12b It Heretic v2?
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 Q5_K_S (8.2 GB file, about 12.0 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 F16 (23.5 GB file, about 27.3 GB in use).
Which Gemma 3 12b It Heretic v2 quant should you choose?
Q4_K_M is the usual starting point for Gemma 3 12b It Heretic v2: 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
Source
Frequently asked questions about Gemma 3 12b It Heretic v2
How much VRAM does Gemma 3 12b It Heretic v2 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 Gemma 3 12b It Heretic v2 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 Gemma 3 12b It Heretic v2 GGUF?
It depends on the quant: Q3_K_M is 6.0 GB, Q4_K_S is 6.9 GB, Q4_K_M is 7.3 GB, Q5_K_S is 8.2 GB, Q5_K_M is 8.4 GB, Q6_K is 9.7 GB and 2 more.
What context length does Gemma 3 12b It Heretic v2 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 Gemma 3 12b It Heretic v2 GGUF?
The files are on Hugging Face in the diffusionmodels1254ani/gemma-3-12b-it-heretic-v2 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 3 12b It Heretic v2 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 Gemma 3 12B IT – Heretic v2 on 8 GB VRAM?
Yes, using the Q3_K_M quantization which requires 9.7 GB memory at 8k context.
Does this model support vision tasks?
Yes, it retains vision_model and multi_modal_projector keys for I2V prompt enhancement.
What is the maximum context length?
The model supports 131072 tokens of context.