HF Model & Benchmark Matrix

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

Kimi-K2.6-Eagle3

nvidia/Kimi-K2.6-Eagle3

kind
original
quant
bf16 (16-bit)
family
kimi
modality
text-generation
root model
moonshotai/Kimi-K2.6
provider
nvidia
license
other
language
—
context
256k
library
Model Optimizer
vRAM (GB)
—
size on disk
—
downloads
4,366
likes
11
created
—
last modified
2026-06-11T06:15:10+00:00 (2026)
huggingface
https://huggingface.co/nvidia/Kimi-K2.6-Eagle3
tags
Model Optimizersafetensorskimi_k2nvidiaModelOptKimi-K2.6Eagle3text-generationarxiv:2503.01840base_model:moonshotai/Kimi-K2.6base_model:finetune:moonshotai/Kimi-K2.6license:otherregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
MATHmath3.23medium| math | 3.23 |
MT-Benchchat2.41low| writing | 2.41 |

Discussions (0)

none scraped.

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