GE

gemma 4 19b a4b it REAP

GemmaGGUF by barozpUpdated 2026-04-06
Download on Hugging Face
Parameters18.4B
Context256K
Layers30
Architecturegemma4
Smallest quant7.8 GB
Quick answer

gemma 4 19b a4b it REAP 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 36.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma‑4‑19B A4B‑IT REAP – 30% expert‑pruned Gemma‑4 model

Gemma‑4‑19B A4B‑IT REAP is a 30% expert‑pruned variant of google/gemma‑4‑26b‑a4b‑it using Cerebras REAP. It retains the original routing behavior and active parameter count per token while reducing disk and memory footprint by ~31%. The model supports reasoning, tools, and vision.

Good at

  • Reasoning
  • Tools integration
  • Vision tasks

Limits

  • No vision support on some platforms
  • Large memory requirement for higher‑quality quants
  • License: gemma

Best for

  • Local inference with limited GPU memory
  • Fine‑tuning on small datasets
  • Deploying on edge devices

Who it’s for. Developers and researchers needing a smaller Gemma‑4 model with preserved routing behavior. Ideal for local deployment where disk space and VRAM are constrained.

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 →
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 →
BF1636.9 GB 45.5 GB
Too big Get file →

For 16 GB VRAM, Q2_K (file size 7.82 GB, estimated 16.4 GB memory at 8 k context) is the lightest option. If 32 GB VRAM is available, Q4_K_S (11.34 GB, 19.9 GB memory) offers better quality. Higher quants such as Q8_0 or BF16 require 28.2 GB or 45.5 GB memory respectively and are suitable only for large‑GPU setups.

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

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).
  • 48 GB VRAM: the best quant that fits is BF16 (36.9 GB file, about 45.5 GB in use).

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

Q4_K_M is the usual starting point for gemma 4 19b a4b it REAP: 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)
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized bybarozp
FamilyGemma
Licensegemma
Downloads (HF)671
Last updated2026-04-06

Frequently asked questions about gemma 4 19b a4b it REAP

How much VRAM does gemma 4 19b a4b it REAP 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 REAP 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 REAP 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, Q4_K_S is 11.3 GB, Q4_K_M is 12.3 GB and 5 more.

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

The files are on Hugging Face in the barozp/gemma-4-19b-a4b-it-REAP-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 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?

No, the smallest quant (Q2_K) requires 16.4 GB memory at 8 k context, exceeding 8 GB VRAM.

Does the model support vision?

Yes, the model has detected vision ability, but some platforms may not expose it.

What is the active parameter count per token?

The active parameter count per token remains ~4 B after pruning.

Other GGUFs of Gemma-4-19B

Similar models

Browse all →

More from barozp

All by barozp →

More Gemma models

All Gemma →

Other medium models

All medium models →