GE

gemma 4 19b a4b it REAP heretic APEX

GemmaGGUF by EmanuelOverrideUpdated 2026-07-09
Download on Hugging Face
Parameters18.4B
Context256K
Layers30
Architecturegemma4
Smallest quant0.0 GB
Quick answer

gemma 4 19b a4b it REAP heretic APEX needs about 18.6 GB of memory at Q4_K_M (a 10.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 0.0 GB to 14.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma 4 19B A4B-it REAP Heretic APEX – 30% MoE pruned, 18.4B parameters

Gemma 4 19B A4B-it REAP Heretic APEX is a mixture‑of‑experts model with 30 transformer layers and sliding attention. It retains 8 active experts per token after 30% expert pruning, preserving routing behavior while reducing disk and memory footprint by ~31%. The model is optimized with custom APEX quantization for efficient inference.

Good at

  • Coding tasks
  • Long‑context generation
  • Stable generation quality

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is gemma

Best for

  • Developers needing efficient MoE inference
  • Researchers testing pruning effects
  • Applications with limited VRAM

Who it’s for. Engineers and researchers who work with Gemma 4 models and require a smaller, efficient variant. The model is suitable for those who can run it on systems with at least 8 GB VRAM and prefer a 30% pruned MoE architecture.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 8.6 GB
Too big Get file →
Q3_K_M9.1 GB 17.7 GB
Too big Get file →
—10.0 GB 18.6 GB
Too big Get file →
Q4_K_M10.1 GB 18.6 GB
Too big Get file →
—11.3 GB 19.8 GB
Too big Get file →
—11.4 GB 20.0 GB
Too big Get file →
Q6_K13.6 GB 22.2 GB
Too big Get file →
Q6_K14.5 GB 23.1 GB
Too big Get file →

For 8 GB VRAM, use the Q3_K_M quant (file size 9.11 GB, estimated memory 17.7 GB at 8k context). If more VRAM is available, Q4_K_M (10.07 GB, 18.6 GB) offers higher precision. For larger budgets, Q6_K variants (13.65 GB/22.2 GB or 14.54 GB/23.1 GB) provide the best accuracy.

What GPU do you need for gemma 4 19b a4b it REAP heretic APEX?

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 the main file (0.0 GB file, about 8.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (14.5 GB file, about 23.1 GB in use).

Which gemma 4 19b a4b it REAP heretic APEX quant should you choose?

Q4_K_M is the usual starting point for gemma 4 19b a4b it REAP heretic APEX: it balances file size and quality well. Here it is a 10.1 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)
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized byEmanuelOverride
FamilyGemma
Licensegemma
Downloads (HF)948
Last updated2026-07-09

Frequently asked questions about gemma 4 19b a4b it REAP heretic APEX

How much VRAM does gemma 4 19b a4b it REAP heretic APEX need?

About 18.6 GB at Q4_K_M with an 8K context window. That is the 10.1 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 19b a4b it REAP heretic APEX 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 REAP heretic APEX GGUF?

It depends on the quant: file is 0.0 GB, Q3_K_M is 9.1 GB, file is 10.0 GB, Q4_K_M is 10.1 GB, file is 11.3 GB, file is 11.4 GB and 2 more.

What context length does gemma 4 19b a4b it REAP heretic APEX 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 REAP heretic APEX GGUF?

The files are on Hugging Face in the EmanuelOverride/gemma-4-19b-a4b-it-REAP-heretic-APEX-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 REAP heretic APEX 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 this model on 8 GB VRAM?

The Q3_K_M quant requires about 17.7 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What is the context length of this model?

The trained context length is 262144 tokens.

Other GGUFs of gemma-4-19b-a4b-it-REAP-heretic

Similar models

Browse all →

More from EmanuelOverride

All by EmanuelOverride →

More Gemma models

All Gemma →

Other medium models

All medium models →