GE

Gemma 4 14B A4B Heretic

GemmaGGUF by mradermacherUpdated 2026-10-12
Download on Hugging Face
Parameters13.8B
Context256K
Layers30
Architecturegemma4
Smallest quant5.9 GB
Quick answer

Gemma 4 14B A4B Heretic needs about 17.8 GB of memory at Q4_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 5.9 GB (Q2_K) to 14.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma 4 14B A4B Heretic – a pruned, Mixture of Experts model

Gemma 4 14B A4B Heretic is a 13.8B parameter model with 4B active experts. It is trained on a 262144 token context and supports reasoning and tool use. The model is a pruned version of Gemma‑4‑26B A4B Heretic.

Good at

  • Reasoning
  • Tool usage
  • Role‑playing

Limits

  • Pruned model may fail on complex math
  • No vision support
  • License not specified

Best for

  • Chatbots needing character consistency
  • Lightweight reasoning tasks
  • Tool‑integrated workflows

Who it’s for. Developers building chat or assistant applications that require consistent role‑playing and reasoning but can tolerate limited math accuracy. Suitable for users with moderate VRAM who prefer a smaller Mixture of Experts model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.9 GB 14.5 GB
Too big Get file →
Q3_K_S6.8 GB 15.3 GB
Too big Get file →
Q3_K_M7.4 GB 15.9 GB
Too big Get file →
Q3_K_L7.7 GB 16.2 GB
Too big Get file →
IQ4_XS7.8 GB 16.3 GB
Too big Get file →
Q4_K_S8.5 GB 17.1 GB
Too big Get file →
Q4_K_M9.2 GB 17.8 GB
Too big Get file →
Q5_K_S9.9 GB 18.4 GB
Too big Get file →
Q5_K_M10.5 GB 19.0 GB
Too big Get file →
Q6_K12.3 GB 20.9 GB
Too big Get file →
Q8_014.7 GB 23.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (5.92 GB file, 14.5 GB memory) or Q3_K_S (6.79 GB file, 15.3 GB memory). If 12 GB VRAM is available, Q4_K_M (9.21 GB file, 17.8 GB memory) offers better quality. Higher quants such as Q8_0 need 23.3 GB memory and are suitable for large‑memory setups.

What GPU do you need for Gemma 4 14B A4B 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: the best quant that fits is Q3_K_M (7.4 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.7 GB file, about 23.3 GB in use).

Which Gemma 4 14B A4B Heretic quant should you choose?

Q4_K_M is the usual starting point for Gemma 4 14B A4B Heretic: it balances file size and quality well. Here it is a 9.2 GB file.

The Q8_0 file is 14.7 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 5.9 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
Parameters13.8B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized bymradermacher
FamilyGemma
Downloads (HF)1,218
Last updated2026-10-12

Frequently asked questions about Gemma 4 14B A4B Heretic

How much VRAM does Gemma 4 14B A4B Heretic need?

About 17.8 GB at Q4_K_M with an 8K context window. That is the 9.2 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 14B A4B Heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 4 14B A4B Heretic GGUF?

It depends on the quant: Q2_K is 5.9 GB, Q3_K_S is 6.8 GB, Q3_K_M is 7.4 GB, Q3_K_L is 7.7 GB, IQ4_XS is 7.8 GB, Q4_K_S is 8.5 GB and 5 more.

What context length does Gemma 4 14B A4B 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 8.1 GB at 8K and 32.2 GB at 32K.

Where can I download Gemma 4 14B A4B Heretic GGUF?

The files are on Hugging Face in the mradermacher/Gemma-4-14B-A4B-Heretic-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Gemma 4 14B A4B Heretic on 8 GB VRAM?

Yes, the Q2_K quant requires 14.5 GB memory at 8 k context, which is within 8 GB VRAM when using llama.cpp with 8 k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the context length of this model?

The trained context length is 262144 tokens.

Other GGUFs of Gemma-4-14B-A4B-Heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other medium models

All medium models →