HF Model & Benchmark Matrix

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

Kimi-K2.6-NVFP4

nvidia/Kimi-K2.6-NVFP4

kind
nvfp4
quant
nvfp4 (4-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
625,624
likes
42
created
—
last modified
2026-05-15T17:40:07+00:00 (2026)
huggingface
https://huggingface.co/nvidia/Kimi-K2.6-NVFP4
tags
Model Optimizersafetensorskimi_k25nvidiaModelOptKimi-K2.6quantizedFP4fp4text-generationconversationalcustom_codebase_model:moonshotai/Kimi-K2.6base_model:quantized:moonshotai/Kimi-K2.6license:othermodeloptregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.

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