GE

gemma-4-12B-it-heretic

GemmaGGUF by JMingoUpdated 2026-06-05
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant4.2 GB
Quick answer

gemma-4-12B-it-heretic needs about 20.5 GB of memory at Q4_K_M (a 7.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 4.2 GB (IQ2_M) to 23.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

Gemma 4 12B instruction-tuned model with multimodal support

Gemma 4 12B instruction-tuned model supports text, image, audio, and video inputs. It offers a 256K token context window and is trained on 11.9B parameters. The model is released under Apache‑2.0.

Good at

  • Coding
  • Multimodal reasoning
  • Text generation

Limits

  • No vision support in this variant
  • Large VRAM required for higher quantizations
  • Requires 8K context for memory estimates

Best for

  • Local code generation
  • Multimodal content creation
  • On‑device inference

Who it’s for. Developers and researchers needing a multimodal LLM for local deployment. The model is open‑source and suitable for laptops and servers with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M4.2 GB 17.6 GB
Too big Get file →
IQ3_XXS4.6 GB 18.0 GB
Too big Get file →
Q2_K_XL4.7 GB 18.0 GB
Too big Get file →
Q3_K_S5.1 GB 18.5 GB
Too big Get file →
Q3_K_M5.7 GB 19.1 GB
Too big Get file →
Q3_K_XL6.0 GB 19.4 GB
Too big Get file →
IQ4_XS6.4 GB 19.8 GB
Too big Get file →
IQ4_NL6.7 GB 20.1 GB
Too big Get file →
Q4_06.7 GB 20.1 GB
Too big Get file →
Q4_K_S6.8 GB 20.1 GB
Too big Get file →
Q4_K_M7.1 GB 20.5 GB
Too big Get file →
Q4_K_XL7.4 GB 20.8 GB
Too big Get file →
Q4_17.4 GB 20.8 GB
Too big Get file →
Q5_K_S8.2 GB 21.6 GB
Too big Get file →
Q5_K_M8.4 GB 21.8 GB
Too big Get file →
Q5_K_XL8.6 GB 22.0 GB
Too big Get file →
Q6_K9.8 GB 23.2 GB
Too big Get file →
Q6_K_XL10.7 GB 24.1 GB
Too big Get file →
Q8_012.7 GB 26.1 GB
Too big Get file →
Q8_K_XL13.6 GB 27.0 GB
Too big Get file →
BF1623.8 GB 37.2 GB
Too big Get file →

For 8 GB VRAM, use IQ2_M (4.21 GB, 17.6 GB memory) or IQ3_XXS (4.64 GB, 18 GB memory). For 16 GB VRAM, Q4_K_M (7.12 GB, 20.5 GB memory) or Q5_K_S (8.2 GB, 21.6 GB memory) are suitable. Higher quants like Q8_0 (12.67 GB, 26.1 GB memory) need 24 GB VRAM or more.

What GPU do you need for gemma-4-12B-it-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: 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_K_XL (13.6 GB file, about 27.0 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 quant should you choose?

Q4_K_M is the usual starting point for gemma-4-12B-it-heretic: it balances file size and quality well. Here it is a 7.1 GB file.

The Q8_0 file is 12.7 GB, about 1.8 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_M at 4.2 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

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

Source

Quantized byJMingo
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,592
Last updated2026-06-05

Frequently asked questions about gemma-4-12B-it-heretic

How much VRAM does gemma-4-12B-it-heretic need?

About 20.5 GB at Q4_K_M with an 8K context window. That is the 7.1 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma-4-12B-it-heretic GGUF?

It depends on the quant: IQ2_M is 4.2 GB, IQ3_XXS is 4.6 GB, Q2_K_XL is 4.7 GB, Q3_K_S is 5.1 GB, Q3_K_M is 5.7 GB, Q3_K_XL is 6.0 GB and 15 more.

What context length does gemma-4-12B-it-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 gemma-4-12B-it-heretic GGUF?

The files are on Hugging Face in the JMingo/gemma-4-12B-it-heretic-UD-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 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?

Yes, using IQ2_M or IQ3_XXS quantizations which fit within 8 GB VRAM and use about 18 GB of RAM at 8K context.

Does this model support vision?

No, the instruction‑tuned variant does not include vision support.

What license applies?

The model is released under the Apache‑2.0 license.

Other GGUFs of gemma-4-12B-it-heretic

Similar models

Browse all →

More from JMingo

All by JMingo →

More Gemma models

All Gemma →

Other medium models

All medium models →