GE

Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking

GemmaGGUF by mradermacherUpdated 2026-04-21
Download on Hugging Face
Parameters18.4B
Context256K
Layers30
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking needs about 20.8 GB of memory at Q4_K_M (a 12.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.0 GB to 16.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking – a large mixture‑of‑experts text model

Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking is a 18.4 billion‑parameter model with 4 billion active experts. It was trained at 16‑bit precision and fine‑tuned on the Deckard dataset. The model supports 262 144‑token context and is fully uncensored.

Good at

  • Coding
  • Reasoning
  • Roleplay

Limits

  • Maximum context 256k tokens
  • Requires large VRAM for higher quants
  • No vision support in this GGUF release

Best for

  • Complex coding tasks
  • Long‑form reasoning
  • Interactive roleplay sessions

Who it’s for. Developers and researchers who need a large, uncensored text model with expert‑mixture capabilities. The model is suitable for applications that can handle its high memory demands and benefit from its extensive context window.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 8.6 GB
Too big Get file →
IQ1_S6.1 GB 14.7 GB
Too big Get file →
IQ1_M6.4 GB 14.9 GB
Too big Get file →
IQ2_XXS6.8 GB 15.4 GB
Too big Get file →
IQ2_XS7.2 GB 15.8 GB
Too big Get file →
IQ2_S7.3 GB 15.8 GB
Too big Get file →
IQ2_M7.6 GB 16.2 GB
Too big Get file →
Q2_K7.8 GB 16.4 GB
Too big Get file →
Q2_K_S7.8 GB 16.4 GB
Too big Get file →
IQ3_XXS8.3 GB 16.9 GB
Too big Get file →
IQ3_XS8.6 GB 17.1 GB
Too big Get file →
IQ3_S9.0 GB 17.5 GB
Too big Get file →
Q3_K_S9.0 GB 17.5 GB
Too big Get file →
IQ3_M9.1 GB 17.7 GB
Too big Get file →
Q3_K_M9.8 GB 18.3 GB
Too big Get file →
Q3_K_L10.2 GB 18.7 GB
Too big Get file →
IQ4_XS10.2 GB 18.8 GB
Too big Get file →
IQ4_NL10.6 GB 19.2 GB
Too big Get file →
Q4_010.6 GB 19.2 GB
Too big Get file →
Q4_K_S11.3 GB 19.9 GB
Too big Get file →
Q4_111.7 GB 20.3 GB
Too big Get file →
Q4_K_M12.3 GB 20.8 GB
Too big Get file →
Q5_K_S13.2 GB 21.7 GB
Too big Get file →
Q5_K_M14.0 GB 22.5 GB
Too big Get file →
Q6_K16.5 GB 25.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.12 GB, 14.7 GB memory at 8k context) or IQ1_M (6.4 GB, 14.9 GB). For 12 GB VRAM, IQ2_S (7.28 GB, 15.8 GB) or Q2_K (7.82 GB, 16.4 GB) are suitable. For 16 GB VRAM, consider IQ3_S (9 GB, 17.5 GB) or Q3_K_M (9.77 GB, 18.3 GB).

What GPU do you need for Gemma 4 19B A4B It The DECKARD 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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 8.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_S (7.3 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (14.0 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (16.5 GB file, about 25.1 GB in use).

Which Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking quant should you choose?

Q4_K_M is the usual starting point for Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking: it balances file size and quality well. Here it is a 12.3 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

Architecturegemma4
Parameters18.4B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Frequently asked questions about Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking

How much VRAM does Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking need?

About 20.8 GB at Q4_K_M with an 8K context window. That is the 12.3 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 4 19B A4B It The DECKARD Heretic Uncensored Thinking on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 6.1 GB, IQ1_M is 6.4 GB, IQ2_XXS is 6.8 GB, IQ2_XS is 7.2 GB, IQ2_S is 7.3 GB and 19 more.

What context length does Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.

Where can I download Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking GGUF?

The files are on Hugging Face in the mradermacher/gemma-4-19B-A4B-it-The-DECKARD-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 4 19B A4B It The DECKARD 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?

Yes, with IQ1_S or IQ1_M quants the estimated VRAM usage is about 14.7–14.9 GB at 8k context, which fits within 8 GB when using efficient batching.

Does this model support vision?

This GGUF release is a text model only; vision support is not included.

What is the maximum context length?

The model supports up to 256k tokens, with a minimum practical context of 8k to 16k tokens.

Other GGUFs of gemma-4-19B-A4B-it-The-DECKARD-Heretic-Uncensored-Thinking

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other medium models

All medium models →