nvidia / text-generation Open weights updated 5 months ago

Kimi-K2.6-NVFP4

Name: Kimi-K2.6-NVFP4
Author: nvidia

The NVIDIA Kimi-K2.6-NVFP4 model is the quantized version of the Moonshot AI's Kimi-K2.6 model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Kimi-K2.6 NVFP4 model is quantized with Model Optimizer.

Params

—

Context

—

Downloads 30d

157 K

Likes

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 19 K in the last 30 days (10.9%)

605 K143 K

Jul 28Sep 1Oct 6Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	fp16	595.2 GB	655.2 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/kimi-k2-6-nvfp4
{
  "hf_id": "nvidia/Kimi-K2.6-NVFP4",
  "params_b": null,
  "context_length": null,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 156813,
  "vram_estimates": [
    { "quant": "fp16", "gb": 655.2 }
  ],
  "updated_at": "2026-07-28T18:04:46Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: KimiK25ForConditionalGeneration
Licence: other
First seen on the Hub: 2026-05-11
Base model: Kimi-K2.6
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base Kimi-K2.6 moonshotai 834 K

Compare with any text-generation model