GE

Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking

GemmaGGUF by mradermacherUpdated 2026-04-12
Download on Hugging Face
Parameters18.4B
Context256K
Layers30
Architecturegemma4
Smallest quant7.8 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 11 quants, from 7.8 GB (Q2_K) to 19.6 GB (Q8_0). 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 18.4B parameter text/image model

Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking is a 18.4B parameter mixture of experts model trained at 16‑bit precision on the Deckard collection. It supports text and image generation and includes a thinking mode that can be toggled via Jinja templates.

Good at

  • Coding
  • Reasoning
  • Roleplay

Limits

  • No vision support beyond image generation
  • Max context 256k, min 8k
  • Requires Apache‑2.0 license compliance

Best for

  • Developer tooling
  • Creative writing
  • AI research

Who it’s for. Engineers and researchers who need a large, uncensored Gemma 4 model with expert pruning and a configurable thinking mode. The model is suitable for applications that require high‑quality text and image generation without external moderation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.8 GB 16.4 GB
Too big Get file →
Q3_K_S9.0 GB 17.5 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_XS10.3 GB 18.9 GB
Too big Get file →
Q4_K_S11.3 GB 19.9 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 →
Q8_019.6 GB 28.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 11.34 GB, estimated 19.9 GB memory). For 12 GB VRAM, Q4_K_M (12.29 GB, 20.8 GB memory). For 16 GB VRAM, Q5_K_S (13.17 GB, 21.7 GB memory).

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: 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 Q5_K_M (14.0 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (19.6 GB file, about 28.2 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.

The Q8_0 file is 19.6 GB, about 1.6 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 7.8 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

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 16.4 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: Q2_K is 7.8 GB, Q3_K_S is 9.0 GB, Q3_K_M is 9.8 GB, Q3_K_L is 10.2 GB, IQ4_XS is 10.3 GB, Q4_K_S is 11.3 GB and 5 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-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, the Q4_K_S quant requires about 19.9 GB memory at 8k context, so 8 GB VRAM is insufficient. Use a larger VRAM or a lower‑precision quant.

Does this model support vision?

It is a text/image model but the provided facts list vision as an ability; however no explicit vision API is mentioned.

What license applies?

The model is released under the Apache‑2.0 license.

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 →