credence:e4b
Credence · Txoka · 7.5B · llama.cpp · Apache-2.0
- Score
- 61.0
- 95 % interval 59.0–62.8
- Rank
- 4
- of 35 scored models
- Public benchmark
- 74.1
- macro accuracy, %
- typed-decisions
- 72.5
- 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 | 74.1(72.8–75.4) | 77.4 | 81.1 | 57.0 | 0.054 | 0.372 | 0 / 3,880 |
| typed-decisions | 72.5(70.3–74.6) | 69.3 | 80.7 | 68.8 | 0.044 | 0.393 | 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 | 121 ms | 123 ms | 17.9 s | 6.2 GB | 8.6 GB | Q8_0 |
| Threadripper 3960X CPU | 4.04 s | 4.11 s | 19.9 s | – | 8.7 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 credence:e4b
# 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 credence:e4b \
--url http://127.0.0.1:11435 --data typed.jsonl --out typed/credence-e4b
# Bespoke Labs' public benchmark; build its 13 subsets first
NIMBLE_SRC=nimble python -m ollaya_convert.bench_public run --model credence:e4b \
--url http://127.0.0.1:11435 --data public --out public/credence-e4b
# speed and memory
python -m ollaya_convert.bench_latency --models credence:e4b --memory \
--machine my-machine --device cuda --out latency.json