winnow:e2b
Winnow · EldanRing · 4.6B · llama.cpp · Apache-2.0
- Score
- 49.4
- 95 % interval 47.3–51.6
- Rank
- 31
- of 66 scored models
- Public benchmark
- 65.9
- macro accuracy, %
- typed-decisions
- 61.6
- accuracy, %
By task
Chance-corrected accuracy on each of the 14 tasks: 0 is guessing, 100 is every answer right.
Accuracy and calibration
| Benchmark | Accuracy | Choice | Noul | Score | ECE | Brier | Rejected |
|---|---|---|---|---|---|---|---|
| Public benchmark | 65.9(64.3–67.3) | 65.4 | 79.6 | 43.8 | 0.191 | 0.514 | 0 / 3,880 |
| typed-decisions | 61.6(59.2–64.0) | 59.5 | 72.0 | 55.4 | 0.146 | 0.532 | 0 / 400 requests |
Accuracy in %, with its 95 % bootstrap interval. A rejected request (the model can’t take the question, or the input is too long for it) counts as wrong.
Speed and memory
| Device | p50 | p90 | Load | VRAM | RAM peak | Precision |
|---|---|---|---|---|---|---|
| RTX 5090 CUDA | 104 ms | 106 ms | 3.86 s | 3.5 GB | 5.0 GB | Q8_0 |
| Threadripper 3960X CPU | 2.04 s | 2.06 s | 10.5 s | – | 4.9 GB | Q8_0 |
Five-question requests over HTTP, one at a time, each a different short message. VRAM: the rise of the GPU’s used memory while the model is loaded. RAM peak: the runner process’s peak resident memory.
Parity with the authors’ code
Its parity check is in the model’s family documentation in the repository (docs/families/); the compiled parity file does not list it yet.
Reproduce
The tools are in convert/ollaya_convert and need only Python’s standard library. Run them against a local Ollaya 0.13.0 with the same model digest.
ollaya pull winnow:e2b
# typed-decisions; export the test split once with
# uv run python -m ollaya_convert.bench_typed export --out typed.jsonl
python -m ollaya_convert.bench_typed run --model winnow:e2b \
--url http://127.0.0.1:11435 --data typed.jsonl --out typed/winnow-e2b
# Bespoke Labs' public benchmark; build its 13 subsets first
NIMBLE_SRC=nimble python -m ollaya_convert.bench_public run --model winnow:e2b \
--url http://127.0.0.1:11435 --data public --out public/winnow-e2b
# speed and memory
python -m ollaya_convert.bench_latency --models winnow:e2b --memory \
--machine my-machine --device cuda --out latency.json