Loading comparison…
HEAD TO HEAD
wfzyx: von and EldanRing: winnow, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | wfzyx/von | eldanring/winnow |
|---|---|---|
| Summary | A ModernBERT-large encoder with an option-marker head. Premise and options are packed into one sequence and each option's marker is scored in a single bidirectional pass; version 1.2 makes the scoring order-invariant. | A Gemma 4 12B fine-tune for typed decisions that also chats and reads images. Ships as GGUF for llama.cpp, holds a 64K context on a 16 GB GPU, and serves /v1/systemone next to /v1/chat/completions. |
| Decides | choice, score, noul, classify | choice, score, noul, classify, route |
| Architecture | von | winnow |
| Fine-tuned from | answerdotai/modernbert-large | google/gemma-4-12b-it |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 63.9% | 85.7% |
| Calibration error | 0.045 | — |
| Valid action rate | — | — |
| Median latency | 18 ms | 143 ms |
| p95 latency | — | — |
| Evaluation suite | JevBench public standard tier | JevBench public subset (231 items), Q8_0 |
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
von is from wfzyx and winnow from EldanRing. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only winnow answers route. winnow reads up to 64K tokens of state, against 8K tokens for von. von is the smaller model, at 395M parameters to 12B.
They report on different suites — von 63.9% on JevBench public standard tier, winnow 85.7% on JevBench public subset (231 items), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
von: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, von answers in about 18 ms at the median and winnow in about 143 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull wfzyx/von and systemone pull eldanring/winnow download the weights.
| Latest version | 1.2.0 | 2026.09 |
|---|
| Variants | — | gguf, SHA256SUMS, LICENSE, NOTICE |
|---|
| Size of latest version | 2.9 GB | 34.2 GB |
|---|
| Files | 2 | 8 |
|---|
| Downloads | 0 | 0 |
|---|
| Stars | 0 | 0 |
|---|
| Tags | system-one, encoder, modernbert, 395m | system-one, gemma, gguf, vision, llama-cpp, 12b |
|---|
| Updated | Sep 27, 2026 | Sep 27, 2026 |
|---|