GE

Winnow E4B

GemmaGGUF by EldanRingUpdated 2026-10-13
Download on Hugging Face
Parameters78M
Context128K
Layers4
Architecturegemma4-assistant
Smallest quant0.2 GB
Quick answer

Winnow E4B needs about 8.6 GB of memory at Q8_0 (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 0.2 GB (BF16) to 15.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.5 GB.

Winnow E4B – a fine‑tuned Gemma 4 E4B for decision making and image input

Winnow E4B is an EldanRing fine‑tune of Gemma 4 E4B IT. It handles typed decisions, chat, and image input without generating explanations. The model is optimized for routing requests, choosing actions, checking conditions, and rating urgency.

Good at

  • Decision‑making with typed options
  • Chat with image input
  • Efficient local inference

Limits

  • No vision support beyond image projector
  • Requires matching projector for images
  • Limited to 8 k context for memory estimates

Best for

  • Routing user requests
  • Choosing actions in workflows
  • Rating urgency in systems

Who it’s for. Developers building decision‑oriented chatbots or agents that need quick, non‑explanatory responses. Suitable for edge devices with limited memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF160.2 GB 0.8 GB
Fits Get file →
Q8_08.0 GB 8.6 GB
Too big Get file →
BF1615.1 GB 15.7 GB
Too big Get file →

For 8 GB VRAM, use Q8_0 (8.01 GB file, 8.6 GB memory at 8 k context). For 4 GB VRAM, use BF16 (0.17 GB file, 0.8 GB memory). Larger memory budgets can use the 15.05 GB BF16 variant.

What GPU do you need for Winnow 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: the best quant that fits is BF16 (0.2 GB file, about 0.8 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (0.2 GB file, about 0.8 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (0.2 GB file, about 0.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 8.6 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (15.1 GB file, about 15.7 GB in use).

Which Winnow E4B quant should you choose?

Q8_0 (8.0 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.

If memory is tight, the smallest file is BF16 at 0.2 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-assistant
Parameters78M
Layers4
Trained context131,072 tokens
KV cache (fp16)16 KB per token

Source

Quantized byEldanRing
FamilyGemma
Licenseapache-2.0
Downloads (HF)44,287
Last updated2026-10-13

Frequently asked questions about Winnow E4B

How much VRAM does Winnow E4B need?

About 8.6 GB at Q8_0 with an 8K context window. That is the 8.0 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 Winnow E4B on an 8 GB GPU?

Yes, with BF16: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Winnow E4B GGUF?

It depends on the quant: BF16 is 0.2 GB, Q8_0 is 8.0 GB, BF16 is 15.1 GB.

What context length does Winnow 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 0.1 GB at 8K and 0.5 GB at 32K.

Where can I download Winnow E4B GGUF?

The files are on Hugging Face in the EldanRing/Winnow-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 Winnow 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 Winnow E4B on 8 GB VRAM?

Yes, the Q8_0 quant uses 8.6 GB memory at 8 k context, fitting within 8 GB VRAM with some headroom.

Does Winnow E4B support video input?

No, video support is not included; only image input via the matching projector is available.

What license applies to Winnow E4B?

The model is released under the Apache 2.0 license.

Other GGUFs of gemma-4-E4B-it

Similar models

Browse all →

More from EldanRing

All by EldanRing →

More Gemma models

All Gemma →

Other tiny models

All tiny models →