FP8 build of
Eikos-27B
: weights in FP8 (per channel) with dynamic FP8 activations (per token), made with llm-compressor (
FP8_DYNAMIC
, compressed-tensors format). No calibration data.
The vision tower, MTP weights, embeddings and LM head are kept in higher precision. The prompt format, the
letter readout and the calibration (
calib.json
, T = 1) are the same as the bf16 model.
Eikos answers typed decisions (yes/no, one of N options, ordinal scores) about a given state in one forward pass,
with a calibrated probability for every option. See the
Eikos-27B card
for what the
model does, how it was trained, the full evaluation and its limitations.
Use
Requires vLLM ≥ 0.30.0.
Older builds return wrong answers when several long requests are batched together on
this hybrid (Gated DeltaNet) architecture.
The HTTP API, agent sessions and the question types are the same as for
Eikos-27B
.
Validation against bf16
Same 7,371 items for both builds (7 suites, never used in training), vLLM 0.30 with batching and prefix cache on.
The release gate was fixed before looking at results: accuracy within 1 point of bf16, ECE within 0.01, and at
least 97% of answers unchanged.
Eikos-27B (bf16)
Eikos-27B-FP8
Size
55.6 GB
31.2 GB
JevBench public — original / hard
100.0 / 82.0
100.0 / 83.8
DecisionBench — medium / hard
89.1 / 78.2
88.7 / 78.8
General battery (9 tasks)
82.6
82.8
Finance (CUAD, sentiment, FinQA-judge)
85.4
85.3
Trade rules — seen / unseen
85.4 / 87.4
85.6 / 86.9
Compositional rules — same type / new domain / rulebooks
95.6 / 94.3 / 95.3
95.6 / 94.7 / 95.0
ECE (lower is better)
0.043
0.042
≥0.90 confidence: decides / error
44.1% / 2.5%
44.2% / 2.6%
Same answer as bf16 (all / confident ≥0.9)
—
98.8% / 100.0%
It passes our release gate.
License
MIT for our contributions (
LICENSE
). The base model, Qwen3.8-27B, is Apache-2.0 (
LICENSE-Qwen
);
attributions are in
NOTICE
. Not legal, tax or investment advice.
Runs of caiovicentino1 Eikos-27B-FP8 on huggingface.co
351
Total runs
8
24-hour runs
21
3-day runs
64
7-day runs
347
30-day runs
More Information About Eikos-27B-FP8 huggingface.co Model
Eikos-27B-FP8 huggingface.co is an AI model on huggingface.co that provides Eikos-27B-FP8's model effect (), which can be used instantly with this caiovicentino1 Eikos-27B-FP8 model. huggingface.co supports a free trial of the Eikos-27B-FP8 model, and also provides paid use of the Eikos-27B-FP8. Support call Eikos-27B-FP8 model through api, including Node.js, Python, http.
Eikos-27B-FP8 huggingface.co is an online trial and call api platform, which integrates Eikos-27B-FP8's modeling effects, including api services, and provides a free online trial of Eikos-27B-FP8, you can try Eikos-27B-FP8 online for free by clicking the link below.
caiovicentino1 Eikos-27B-FP8 online free url in huggingface.co:
Eikos-27B-FP8 is an open source model from GitHub that offers a free installation service, and any user can find Eikos-27B-FP8 on GitHub to install. At the same time, huggingface.co provides the effect of Eikos-27B-FP8 install, users can directly use Eikos-27B-FP8 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.