GE

Storyteller Gemma3 27B

GemmaGGUF by mradermacherUpdated 2026-10-06
Download on Hugging Face
Parameters28.4B
Context128K
Layers62
Architecturegemma3
Smallest quant6.7 GB
Quick answer

Storyteller Gemma3 27B needs about 22.0 GB of memory at Q4_K_M (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 6.7 GB (IQ1_S) to 23.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

Storyteller Gemma3 27B – 28.4B parameter text model

Storyteller Gemma3 27B is a 28.4B parameter model based on the Gemma3 architecture. It supports a context length of 131072 tokens and is available in a variety of GGUF quantizations. The model is suitable for large‑scale text generation tasks.

Good at

  • High‑capacity text generation
  • Long‑form dialogue
  • Complex reasoning

Limits

  • No vision support
  • Large memory requirement for full precision
  • No license information

Best for

  • Chatbot back‑ends
  • Creative writing assistants
  • Research prototypes

Who it’s for. Developers and researchers needing a large language model with extensive context. The model can be run locally with llama.cpp using the provided GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S6.7 GB 11.4 GB
Too big Get file →
IQ1_M7.3 GB 11.9 GB
Too big Get file →
IQ2_XXS8.1 GB 12.8 GB
Too big Get file →
IQ2_XS8.9 GB 13.6 GB
Too big Get file →
IQ2_S9.4 GB 14.0 GB
Too big Get file →
IQ2_M10.1 GB 14.8 GB
Too big Get file →
Q2_K_S10.2 GB 14.9 GB
Too big Get file →
Q2_K11.0 GB 15.6 GB
Too big Get file →
IQ3_XXS11.3 GB 16.0 GB
Too big Get file →
IQ3_XS12.2 GB 16.8 GB
Too big Get file →
IQ3_S12.8 GB 17.4 GB
Too big Get file →
Q3_K_S12.8 GB 17.4 GB
Too big Get file →
IQ3_M13.2 GB 17.8 GB
Too big Get file →
Q3_K_M14.0 GB 18.7 GB
Too big Get file →
Q3_K_L15.1 GB 19.8 GB
Too big Get file →
IQ4_XS15.5 GB 20.2 GB
Too big Get file →
Q4_016.4 GB 21.1 GB
Too big Get file →
Q4_K_S16.5 GB 21.1 GB
Too big Get file →
Q4_K_M17.3 GB 22.0 GB
Too big Get file →
Q4_118.0 GB 22.7 GB
Too big Get file →
Q5_K_S19.7 GB 24.4 GB
Too big Get file →
Q5_K_M20.2 GB 24.9 GB
Too big Get file →
Q6_K23.3 GB 28.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.73 GB file, 11.4 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (8.9 GB file, 13.6 GB memory). For 16 GB VRAM, Q4_K_S (16.47 GB file, 21.1 GB memory). Estimates are approximate.

What GPU do you need for Storyteller Gemma3 27B?

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 IQ1_M (7.3 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (11.3 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (18.0 GB file, about 22.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (23.3 GB file, about 28.0 GB in use).

Which Storyteller Gemma3 27B quant should you choose?

Q4_K_M is the usual starting point for Storyteller Gemma3 27B: it balances file size and quality well. Here it is a 17.3 GB file.

If memory is tight, the smallest file is IQ1_S at 6.7 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

Architecturegemma3
Parameters28.4B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized bymradermacher
FamilyGemma
Downloads (HF)1,538
Last updated2026-10-06

Frequently asked questions about Storyteller Gemma3 27B

How much VRAM does Storyteller Gemma3 27B need?

About 22.0 GB at Q4_K_M with an 8K context window. That is the 17.3 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 Storyteller Gemma3 27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Storyteller Gemma3 27B GGUF?

It depends on the quant: IQ1_S is 6.7 GB, IQ1_M is 7.3 GB, IQ2_XXS is 8.1 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.4 GB, IQ2_M is 10.1 GB and 17 more.

What context length does Storyteller Gemma3 27B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download Storyteller Gemma3 27B GGUF?

The files are on Hugging Face in the mradermacher/Storyteller-gemma3-27B-i1-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 Storyteller Gemma3 27B on 8 GB VRAM?

Use the IQ1_S quant which requires about 11.4 GB memory at 8 k context. It may fit with lower batch sizes.

Does this model support vision tasks?

No, the model is a text‑only model; vision support is not included.

What is the maximum context length?

The model supports up to 131072 tokens of context.

Other GGUFs of Storyteller-gemma3-27B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other medium models

All medium models →