HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

DeepSeek-V3-0324

deepseek-ai/DeepSeek-V3-0324

kind
fp8
quant
fp8 (8-bit)
family
deepseek
modality
text-generation
root model
deepseek-ai/DeepSeek-V3-0324
provider
deepseek-ai
license
mit
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
835,522
likes
3,148
created
—
last modified
2025-03-27T04:01:53+00:00 (2025)
huggingface
https://huggingface.co/deepseek-ai/DeepSeek-V3-0324
tags
transformerssafetensorsdeepseek_v3text-generationconversationalcustom_codearxiv:2412.19437license:miteval-resultstext-generation-inferenceendpoints_compatiblefp8region:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
MMLU-Proknowledge75.9mediumMMLU-Pro: 75.9
GPQAreasoning59.1mediumGPQA: 59.1
LiveCodeBenchcoding39.2mediumLiveCodeBench: 39.2

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.