GE

Credence v1 Gemma4 E4B

GemmaGGUF by TxokaUpdated 2026-10-08
Download on Hugging Face
Parameters8.19B
Context128K
Layers42
Architecturegemma4
Smallest quant8.7 GB
Quick answer

Credence v1 Gemma4 E4B needs about 10.6 GB of memory at Q8_0 (a 8.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.7 GB (Q8_0) to 8.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Credence v1 Gemma4 E4B – a decision‑oriented Gemma4 model

Credence v1 Gemma4 E4B is a fine‑tuned Gemma4 E4B model optimized for decision making and reasoning. It supports image input via a vision projector and is released under the apache-2.0 license. The model is available in a Q8_0 GGUF format.

Good at

  • Decision making
  • Reasoning
  • Vision input

Limits

  • No conversational mode
  • Requires 8.72 GB GGUF file
  • Needs 10.6 GB VRAM at 8 k context

Best for

  • Routing requests
  • Choosing actions
  • Rating urgency

Who it’s for. Developers building decision‑support systems or chatbots that need fast, accurate choices. The model is suitable for applications that require image‑based reasoning and a lightweight inference footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_08.7 GB 10.6 GB
Too big Get file →
Q8_08.7 GB 10.6 GB
Too big Get file →

The only available quant is Q8_0, 8.72 GB in size. It requires approximately 10.6 GB of VRAM at an 8 k context length. For systems with less memory, a lower‑precision quant would be needed, but none is provided in the current file list.

What GPU do you need for Credence v1 Gemma4 E4B?

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 Q8_0 (8.7 GB file, about 10.6 GB in use).

Which Credence v1 Gemma4 E4B quant should you choose?

Q8_0 (8.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters8.19B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byTxoka
FamilyGemma
Licenseapache-2.0
Downloads (HF)693
Last updated2026-10-08

Frequently asked questions about Credence v1 Gemma4 E4B

How much VRAM does Credence v1 Gemma4 E4B need?

About 10.6 GB at Q8_0 with an 8K context window. That is the 8.7 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 Credence v1 Gemma4 E4B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Credence v1 Gemma4 E4B GGUF?

It depends on the quant: Q8_0 is 8.7 GB, Q8_0 is 8.7 GB.

What context length does Credence v1 Gemma4 E4B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Credence v1 Gemma4 E4B GGUF?

The files are on Hugging Face in the Txoka/Credence-v1-Gemma4-E4B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Credence v1 Gemma4 E4B 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 Credence v1 Gemma4 E4B on 8 GB VRAM?

The Q8_0 quant requires about 10.6 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does the model support image input?

Yes, image input is supported via the matching vision projector included with the GGUF download.

Is the model licensed for commercial use?

It is released under the apache-2.0 license, which permits commercial use.

Similar models

Browse all →

More from Txoka

All by Txoka →

More Gemma models

All Gemma →

Other small models

All small models →