credence:e4b-calibrated
Credence · Txoka · 7.5B · llama.cpp · Apache-2.0
- Score
- 60.5
- 95 % interval 58.6–62.4
- Rank
- 6
- of 35 scored models
- Public benchmark
- 73.7
- macro accuracy, %
- typed-decisions
- 72.4
- 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 | 73.7(72.3–75.1) | 76.8 | 81.0 | 56.3 | 0.038 | 0.369 | 0 / 3,880 |
| typed-decisions | 72.4(70.0–74.8) | 69.8 | 79.2 | 69.1 | 0.044 | 0.398 | 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 | 114 ms | 115 ms | 17.4 s | 6.2 GB | 8.6 GB | Q8_0 |
| Threadripper 3960X CPU | 4.10 s | 4.18 s | 19.5 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-calibrated
# 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-calibrated \
--url http://127.0.0.1:11435 --data typed.jsonl --out typed/credence-e4b-calibrated
# Bespoke Labs' public benchmark; build its 13 subsets first
NIMBLE_SRC=nimble python -m ollaya_convert.bench_public run --model credence:e4b-calibrated \
--url http://127.0.0.1:11435 --data public --out public/credence-e4b-calibrated
# speed and memory
python -m ollaya_convert.bench_latency --models credence:e4b-calibrated --memory \
--machine my-machine --device cuda --out latency.json