GE

Winnow E2B

GemmaGGUF by EldanRingUpdated 2026-10-13
Download on Hugging Face
Parameters77M
Context128K
Layers4
Architecturegemma4-assistant
Smallest quant0.2 GB
Quick answer

Winnow E2B needs about 5.5 GB of memory at Q8_0 (a 5.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 0.2 GB (BF16) to 9.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.

Winnow E2B – a fine‑tuned Gemma 4 E2B for decision tasks

Winnow E2B is a decision‑fine‑tuned version of Gemma 4 E2B IT. It supports text chat and image input via a matching vision projector. The model is available in BF16 and Q8_0 GGUF formats.

Good at

  • Decision scoring
  • Image‑text multimodal input
  • Text chat

Limits

  • No vision support beyond images
  • Requires matching projector for images
  • Large VRAM needed for Q8_0

Best for

  • Decision‑making chatbots
  • Image‑based QA
  • Fine‑tuned instruction tasks

Who it’s for. Developers building decision‑oriented chat interfaces or multimodal assistants that need a lightweight, locally deployable model. The model is suitable for edge devices with sufficient VRAM for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF160.2 GB 0.7 GB
Fits Get file →
Q8_05.0 GB 5.5 GB
Fits Get file →
BF169.3 GB 9.9 GB
Too big Get file →

For 8 GB VRAM, use the Q8_0 GGUF (file size 4.95 GB, estimated 5.5 GB memory at 8 k context). If VRAM is limited, the BF16 GGUF (file size 0.17 GB, estimated 0.7 GB memory) is a viable alternative.

What GPU do you need for Winnow E2B?

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 0.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (5.0 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.0 GB file, about 5.5 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (9.3 GB file, about 9.9 GB in use).

Which Winnow E2B quant should you choose?

Q8_0 (5.0 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
Parameters77M
Layers4
Trained context131,072 tokens
KV cache (fp16)8 KB per token

Source

Quantized byEldanRing
FamilyGemma
Licenseapache-2.0
Downloads (HF)3,074
Last updated2026-10-13

Frequently asked questions about Winnow E2B

How much VRAM does Winnow E2B need?

About 5.5 GB at Q8_0 with an 8K context window. That is the 5.0 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 E2B on an 8 GB GPU?

Yes, with Q8_0: the 5.0 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Winnow E2B GGUF?

It depends on the quant: BF16 is 0.2 GB, Q8_0 is 5.0 GB, BF16 is 9.3 GB.

What context length does Winnow E2B 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 0.3 GB at 32K.

Where can I download Winnow E2B GGUF?

The files are on Hugging Face in the EldanRing/Winnow-E2B 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 E2B 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 E2B on 8 GB VRAM?

Yes, the Q8_0 GGUF requires about 5.5 GB memory at 8 k context, which fits in 8 GB VRAM.

Does Winnow E2B support video input?

No, only text and image input are supported; video is not available.

What cache precision is recommended?

F16 is the default and recommended target K/V cache for best performance.

Other GGUFs of gemma-4-E2B-it

Similar models

Browse all →

More from EldanRing

All by EldanRing →

More Gemma models

All Gemma →

Other tiny models

All tiny models →