EldanRingE4B (8B total)~6 GB VRAM at Q4_K_M

Winnow E4B — VRAM & /v1/systemone setup

Written by Jakub Rusinowski · Last updated

EldanRing's E4B (8B total) decision model on Gemma 4 E4B, served by winnow-inference alongside chat and vision.

Winnow E4B needs about 6 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Call Winnow E4B

Served by winnow-inference (default port 8091). This model does not run in Ollama.

Question types
choice noul (yes / no) score
Inputs
text image
Serve with
winnow-inference :8091
Endpoint
/v1/systemone

http://localhost:8091/v1/systemone

Setup for servers other than Ollama →

Weights on Hugging Face: EldanRing/Winnow-E4B ↗

Build a request for this model Decision models guide

Other decision models: Nimble 9B · Tev1 4B · Tev1 0.8B · Winnow 12B · Decider 2B · Decider 4B · Decider 35B-A3B (NVFP4) · Decider 12B Vision · Decider 31B v2 (NVFP4) · JevK5 4B · Intern-Decision 4B · AutoJev 27B · Laya · Clef 27B · Clef-Flash 9B · Rune 26B-A4B v3 · OpenDecider-nano · OpenDecider-small · OpenDecider-small MLX 4-bit · Bosun v3.1 0.6B · Bosun v3.1 1.7B · d1-3B · d1-omni-600M · THX-01 322M · mammoth-1 27B · elephant-1 9B · Strands Decider 2B (hobson-v21) · kev 4B · kev 9B · OpenJev 27B

Hardware fit

Weights plus overhead plus the KV cache at a 8,192-token prompt, on NVIDIA RTX 4090 (24 GB). A publisher build is sized from its file; the other rows are modelled at a standard quant. Decision requests are short, so no long-context figure is shown. Image tokens are not modelled: each image adds to the prompt, so a request with images needs more memory than these rows.

QuantVRAMFit
BF16
Publisher build · 15.05 GB file
17 GBFits
Q4_K_M
4.83 bpw · modelled quant
6.8 GBFits
Q6_K
6.56 bpw · modelled quant
8.5 GBFits
Q8_0
8.50 bpw · modelled quant
10 GBFits

Published file size: Q8_0 8.01 GB · BF16 15.05 GB. A download size from the model publisher — not a VRAM requirement.

How it was scored

Two different suites on two different scales. Never compare the numbers across the two cards.

Decision Index 0.2.1 (snapshot 2026-09-28)

Decision Index 0.2.1Community Decision Index (not by the model's authors)
Balanced skill39.89
ECE (lower is better)
0.058
Median compute
45 ms on 1x NVIDIA RTX PRO 6000 (96 GB)

Community-maintained; not affiliated with the model authors.

Source ↗

Decision models are not ranked on chat, creative or coding scores.

Specifications

Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source. Still unconfirmed: weightsGbByQuant.

Parameters
E4B (8B total)
Context window
Not published
Architecture
Fine-tune of google/gemma-4-E4B
Provider
EldanRing
Licence
Apache-2.0
Practical deployment
Laptop
Specified at
Q4_K_M
System RAM
12 GB
Record updated
2026-09-30
LicenceApache-2.0Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Other Winnow sizes

Winnow E4B — frequently asked questions

What is Winnow E4B?

Winnow E4B is a decision model: you send it a state and typed questions (choice, yes/no/unknown, or a score) and it returns one answer per question with a probability for every option. It is not a chat model.

How do I run Winnow E4B locally?

Winnow E4B does not run in Ollama. Served by winnow-inference (default port 8091). This model does not run in Ollama. See the setup guide for servers other than Ollama.

How much memory does Winnow E4B need?

About 6 GB for the weights plus overhead at Q4_K_M, before the prompt's KV cache. Decision prompts are short, so the cache stays small.

How accurate is Winnow E4B?

Its published score is on the community Decision Index 0.2.1, which its authors did not build. It is not a calibration guarantee: test on your own examples.