HF Model & Benchmark Matrix

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

Moonlight-16B-A3B

moonshotai/Moonlight-16B-A3B

kind
original
quant
bf16 (16-bit)
family
kimi
modality
text-generation
root model
moonshotai/Moonlight-16B-A3B
provider
moonshotai
license
mit
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
10,769
likes
114
created
—
last modified
2026-01-30T04:51:48+00:00 (2026)
huggingface
https://huggingface.co/moonshotai/Moonlight-16B-A3B
tags
transformerssafetensorsdeepseek_v3text-generationconversationalcustom_codearxiv:2502.16982license:mittext-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
MATHmath34.0**Math**medium| **Math** | GSM8K | 34.0 | **79.1** | 41.1 | 77.4 |

Discussions (0)

none scraped.

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