GE

Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking

GemmaGGUF by mradermacherUpdated 2026-04-02
Download on Hugging Face
Parameters40B
Context128K
Layers94
Architecturegemma3
Smallest quant0.0 GB
Quick answer

Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking needs about 31.3 GB of memory at Q4_K_M (a 24.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.0 GB to 33.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 25.2 GB.

Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking – 40B vision and reasoning model

Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking is a 40 billion‑parameter vision‑language model. It supports coding, reasoning, roleplay, and image understanding. The model is fully uncensored and trained on a GEMINI reasoning dataset.

Good at

  • Vision and image captioning
  • Complex reasoning tasks
  • Code generation

Limits

  • Requires large VRAM – 20 GB+ for high‑quality quants
  • No built‑in safety filters
  • Large context window limits to 131072 tokens

Best for

  • Developers building multimodal assistants
  • Researchers testing reasoning capabilities
  • Creative content generation with images

Who it’s for. The model is suited for users who need advanced vision‑language reasoning without safety constraints. It is ideal for developers, researchers, and content creators who can manage high memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 6.8 GB
Fits Get file →
IQ1_S9.0 GB 15.8 GB
Too big Get file →
IQ1_M9.8 GB 16.6 GB
Too big Get file →
IQ2_XXS11.2 GB 18.0 GB
Too big Get file →
IQ2_XS12.3 GB 19.1 GB
Too big Get file →
IQ2_S12.8 GB 19.6 GB
Too big Get file →
IQ2_M13.9 GB 20.7 GB
Too big Get file →
Q2_K_S14.2 GB 21.0 GB
Too big Get file →
Q2_K15.3 GB 22.1 GB
Too big Get file →
IQ3_XXS15.7 GB 22.6 GB
Too big Get file →
IQ3_XS16.9 GB 23.7 GB
Too big Get file →
IQ3_S17.8 GB 24.7 GB
Too big Get file →
Q3_K_S17.8 GB 24.7 GB
Too big Get file →
IQ3_M18.4 GB 25.2 GB
Too big Get file →
Q3_K_M19.8 GB 26.6 GB
Too big Get file →
Q3_K_L21.4 GB 28.3 GB
Too big Get file →
IQ4_XS21.8 GB 28.6 GB
Too big Get file →
Q4_023.1 GB 29.9 GB
Too big Get file →
Q4_K_S23.2 GB 30.0 GB
Too big Get file →
Q4_K_M24.5 GB 31.3 GB
Too big Get file →
Q4_125.4 GB 32.2 GB
Too big Get file →
Q5_K_S27.9 GB 34.7 GB
Too big Get file →
Q5_K_M28.6 GB 35.4 GB
Too big Get file →
Q6_K33.0 GB 39.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 23.17 GB, memory 30 GB at 8k context). For 12 GB VRAM, Q4_K_M (24.5 GB, 31.3 GB). For 16 GB VRAM, Q5_K_S (27.85 GB, 34.7 GB). Higher quants give better quality but need more memory.

What GPU do you need for Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking?

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 the main file (0.0 GB file, about 6.8 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 6.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ1_S (9.0 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_XS (16.9 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (24.5 GB file, about 31.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (33.0 GB file, about 39.8 GB in use).

Which Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking quant should you choose?

Q4_K_M is the usual starting point for Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking: it balances file size and quality well. Here it is a 24.5 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

Architecturegemma3
Parameters40B
Layers94
Trained context131,072 tokens
KV cache (fp16)752 KB per token

Frequently asked questions about Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking

How much VRAM does Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking need?

About 31.3 GB at Q4_K_M with an 8K context window. That is the 24.5 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 It Vl 40B Gemini Heretic Uncensored Thinking on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 9.0 GB, IQ1_M is 9.8 GB, IQ2_XXS is 11.2 GB, IQ2_XS is 12.3 GB, IQ2_S is 12.8 GB and 18 more.

What context length does Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 6.3 GB at 8K and 25.2 GB at 32K.

Where can I download Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking GGUF?

The files are on Hugging Face in the mradermacher/gemma-3-it-vl-40B-Gemini-Heretic-Uncensored-Thinking-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 Gemma 3 It Vl 40B Gemini Heretic Uncensored Thinking 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 this model on 8 GB VRAM?

Use the Q4_K_S quant; it requires approximately 30 GB of VRAM at 8k context, so 8 GB is insufficient.

Does this model have safety filters?

No, the model is fully uncensored and has no built‑in safety filters.

What is the maximum context length?

The model supports up to 131072 tokens of context.

Other GGUFs of gemma-3-it-vl-40B-Gemini-Heretic-Uncensored-Thinking

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other large models

All large models →