GE

gemma4 31b novelbuds agent

GemmaGGUF by saneavenUpdated 2026-09-30
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant11.5 GB
Quick answer

gemma4 31b novelbuds agent needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 11.5 GB (BF16) to 18.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Gemma 4 31B Novel Buds Agent – a fine‑tuned creative‑writing assistant

Gemma 4 31B Novel Buds Agent is a domain‑specific agent for novel‑writing workflows. It can discuss story ideas, inspect project context, and produce tool calls for characters, outlines, manuscript text, and timelines.

Good at

  • Creative writing assistance
  • Tool‑using dialogue
  • Context inspection

Limits

  • No vision support beyond basic detection
  • Large memory requirement
  • No license information provided

Best for

  • Novel brainstorming
  • Character development
  • Worldbuilding scripts

Who it’s for. Developers building creative‑writing assistants or researchers experimenting with tool‑using LLMs. The model is tailored for novel‑writing contexts and requires substantial GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1611.5 GB 44.2 GB
Too big Get file →
Q4_K_M18.7 GB 51.4 GB
Too big Get file →

For 8k context, the BF16 file (~11.48 GB) uses about 44.2 GB of VRAM. The Q4_K_M file (~18.69 GB) uses about 51.4 GB of VRAM. Choose the quant that fits your memory budget; both are approximate estimates.

What GPU do you need for gemma4 31b novelbuds agent?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is BF16 (11.5 GB file, about 44.2 GB in use).

Which gemma4 31b novelbuds agent quant should you choose?

Q4_K_M is the usual starting point for gemma4 31b novelbuds agent: it balances file size and quality well. Here it is a 18.7 GB file.

If memory is tight, the smallest file is BF16 at 11.5 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized bysaneaven
FamilyGemma
Downloads (HF)145
Last updated2026-09-30

Frequently asked questions about gemma4 31b novelbuds agent

How much VRAM does gemma4 31b novelbuds agent need?

About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 31b novelbuds agent on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma4 31b novelbuds agent GGUF?

It depends on the quant: BF16 is 11.5 GB, Q4_K_M is 18.7 GB.

What context length does gemma4 31b novelbuds agent support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download gemma4 31b novelbuds agent GGUF?

The files are on Hugging Face in the saneaven/gemma4-31b-novelbuds-agent-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 this model on 8 GB VRAM?

No, the model requires over 44 GB of VRAM for 8k context.

Does it support vision?

The model detects vision abilities but does not provide vision inference.

Is it a mixture of experts?

No, it is not a mixture of experts.

Similar models

Browse all →

More from saneaven

All by saneaven →

More Gemma models

All Gemma →

Other medium models

All medium models →