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.
http://localhost:8091/v1/systemone
Setup for servers other than Ollama →
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) · JevK5 4B · Intern-Decision 4B · AutoJev 27B · Laya
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.
| Quant | Memory | VRAM | Fit |
|---|---|---|---|
| BF16 Publisher build · 15.05 GB file | 17 GB | Fits | |
| Q4_K_M 4.83 bpw · modelled quant | 6.8 GB | Fits | |
| Q6_K 6.56 bpw · modelled quant | 8.5 GB | Fits | |
| Q8_0 8.50 bpw · modelled quant | 10 GB | Fits |
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 0.2.1- 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
- Specified at
- Q4_K_M
- System RAM
- 12 GB
- Record updated
- 2026-09-30
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?
It has two separate published scores on two different suites — the author's own benchmark and the community Decision Index 0.2.1. They are not comparable with each other, and neither is a calibration guarantee.