EnsueAI
/

DeepSeek-V4-Flash-Base-INT4

Mixture of Experts

Model card Files Files and versions

DeepSeek-V4-Flash-Base-INT4 / tokenizer.json

zyan1deOG's picture

V4-Flash-Base INT4 Tier-A overlay (~70% coverage, MMLU Δ 0.8 pp, ~90 GiB on-disk savings)

aeacbcb verified 6 months ago

Raw History Contribute Delete

6.37 MB

File too large to display, you can check the raw version instead.