SM

Smaug Humanizer

SmaugGGUF by mradermacherUpdated 2026-10-27
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Smaug Humanizer needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.0 GB to 9.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

Smaug Humanizer – a 11.9B gemma4 model for text generation

Smaug Humanizer is a 11.9B parameter gemma4 model. It supports a 262144 token context window and is released under the apache-2.0 license. The model is available in multiple quantizations for different memory budgets.

Good at

  • Large context handling
  • High parameter count
  • Versatile quant options

Limits

  • No vision support in the provided GGUFs
  • Requires 8k context for memory estimates
  • No mixture of experts

Best for

  • Long-form content creation
  • Complex dialogue systems
  • Research prototyping

Who it’s for. Developers and researchers needing a large gemma4 model with flexible quantization options. The model is suitable for environments where memory constraints can be managed with the available quant files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 13.4 GB
Too big Get file →
IQ1_S3.0 GB 16.4 GB
Too big Get file →
IQ1_M3.2 GB 16.6 GB
Too big Get file →
IQ2_XXS3.6 GB 17.0 GB
Too big Get file →
IQ2_XS3.9 GB 17.3 GB
Too big Get file →
IQ2_S4.1 GB 17.5 GB
Too big Get file →
IQ2_M4.4 GB 17.8 GB
Too big Get file →
Q2_K_S4.5 GB 17.9 GB
Too big Get file →
Q2_K4.8 GB 18.2 GB
Too big Get file →
IQ3_XXS4.8 GB 18.2 GB
Too big Get file →
IQ3_XS5.3 GB 18.7 GB
Too big Get file →
IQ3_S5.5 GB 18.9 GB
Too big Get file →
Q3_K_S5.5 GB 18.9 GB
Too big Get file →
IQ3_M5.7 GB 19.1 GB
Too big Get file →
Q3_K_M6.1 GB 19.5 GB
Too big Get file →
Q3_K_L6.6 GB 20.0 GB
Too big Get file →
IQ4_XS6.6 GB 20.0 GB
Too big Get file →
IQ4_NL7.0 GB 20.4 GB
Too big Get file →
Q4_07.0 GB 20.4 GB
Too big Get file →
Q4_K_S7.0 GB 20.4 GB
Too big Get file →
Q4_K_M7.4 GB 20.8 GB
Too big Get file →
Q4_17.7 GB 21.0 GB
Too big Get file →
Q5_K_S8.3 GB 21.7 GB
Too big Get file →
Q5_K_M8.5 GB 21.9 GB
Too big Get file →
Q6_K9.8 GB 23.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.98 GB) or IQ1_M (3.2 GB). For 16 GB VRAM, Q4_K_M (7.38 GB) or Q5_K_M (8.55 GB) are suitable. Larger models like Q6_K (9.79 GB) require more than 16 GB VRAM.

What GPU do you need for Smaug Humanizer?

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 the main file (0.0 GB file, about 13.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).

Which Smaug Humanizer quant should you choose?

Q4_K_M is the usual starting point for Smaug Humanizer: it balances file size and quality well. Here it is a 7.4 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
Parameters11.9B
Layers48
Trained context262,144 tokens
KV cache (fp16)1536 KB per token

Source

Quantized bymradermacher
FamilySmaug
Licenseapache-2.0
Downloads (HF)3,946
Last updated2026-10-27

Frequently asked questions about Smaug Humanizer

How much VRAM does Smaug Humanizer need?

About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 Smaug Humanizer on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Smaug Humanizer GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.1 GB and 19 more.

What context length does Smaug Humanizer support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.

Where can I download Smaug Humanizer GGUF?

The files are on Hugging Face in the mradermacher/Smaug-Humanizer-i1-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 Smaug Humanizer 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 Smaug Humanizer on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quant files, which are 2.98 GB and 3.2 GB respectively.

Does this model support vision tasks?

No, the provided GGUF files are text-only. Vision support would require mmproj files not included here.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Smaug models

All Smaug →

Other medium models

All medium models →