GE

Gemma4 26B A4B Korean Opus 4.6 Distilled

GemmaGGUF by mradermacherUpdated 2026-10-12
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant10.6 GB
Quick answer

Gemma4 26B A4B Korean Opus 4.6 Distilled needs about 25.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 10.6 GB (Q2_K) to 26.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma4 26B Korean reasoning model distilled from Claude Opus 4.6

Gemma4 26B A4B Korean Opus 4.6 Distilled is a 25.2 billion‑parameter model fine‑tuned for Korean reasoning. It supports reasoning and vision tasks and was trained on 12 k Korean reasoning data. The model is released under apache‑2.0.

Good at

  • Korean reasoning
  • Vision tasks
  • Large context 262 144 tokens

Limits

  • Mixture of experts requires more memory
  • No explicit vision support beyond basic detection
  • License is apache‑2.0

Best for

  • Korean language chatbots
  • Document summarization in Korean
  • Vision‑enabled Korean QA

Who it’s for. Developers building Korean language applications that need reasoning and basic vision capabilities. The model is suitable for research and production use where a large context window is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.6 GB 19.1 GB
Too big Get file →
Q3_K_S12.2 GB 20.8 GB
Too big Get file →
Q3_K_M13.3 GB 21.8 GB
Too big Get file →
Q3_K_L13.8 GB 22.4 GB
Too big Get file →
IQ4_XS14.1 GB 22.6 GB
Too big Get file →
Q4_K_S15.5 GB 24.0 GB
Too big Get file →
Q4_K_M16.8 GB 25.3 GB
Too big Get file →
Q5_K_S18.0 GB 26.5 GB
Too big Get file →
Q5_K_M19.1 GB 27.7 GB
Too big Get file →
Q6_K22.6 GB 31.2 GB
Too big Get file →
Q8_026.9 GB 35.4 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (10.58 GB file, ~19.1 GB memory at 8 k context). For 12 GB VRAM, Q3_K_S (12.22 GB file, ~20.8 GB memory). For 16 GB VRAM, Q4_K_S (15.46 GB file, ~24 GB memory).

What GPU do you need for Gemma4 26B A4B Korean Opus 4.6 Distilled?

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 Q4_K_S (15.5 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).

Which Gemma4 26B A4B Korean Opus 4.6 Distilled quant should you choose?

Q4_K_M is the usual starting point for Gemma4 26B A4B Korean Opus 4.6 Distilled: it balances file size and quality well. Here it is a 16.8 GB file.

The Q8_0 file is 26.9 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 10.6 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
Parameters25.2B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized bymradermacher
FamilyGemma
Licenseapache-2.0
Downloads (HF)986
Last updated2026-10-12

Frequently asked questions about Gemma4 26B A4B Korean Opus 4.6 Distilled

How much VRAM does Gemma4 26B A4B Korean Opus 4.6 Distilled need?

About 25.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Gemma4 26B A4B Korean Opus 4.6 Distilled on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma4 26B A4B Korean Opus 4.6 Distilled GGUF?

It depends on the quant: Q2_K is 10.6 GB, Q3_K_S is 12.2 GB, Q3_K_M is 13.3 GB, Q3_K_L is 13.8 GB, IQ4_XS is 14.1 GB, Q4_K_S is 15.5 GB and 5 more.

What context length does Gemma4 26B A4B Korean Opus 4.6 Distilled 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 Gemma4 26B A4B Korean Opus 4.6 Distilled GGUF?

The files are on Hugging Face in the mradermacher/Gemma4-26B-A4B-Korean-Opus-4.6-Distilled-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 Gemma4 26B A4B Korean Opus 4.6 Distilled 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 Q2_K quant uses 10.58 GB file size and requires about 19.1 GB memory at 8 k context, which is within 8 GB VRAM when using efficient memory management.

Does this model support vision tasks?

The model has detected vision abilities, but it is primarily designed for reasoning. Vision support is basic and may require additional configuration.

What license applies to this model?

The model is released under the apache‑2.0 license, allowing free use and modification.

Other GGUFs of KoGemopus-4-26B-A4B-experimental

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other medium models

All medium models →