The real cost to run A.X K1

skt · 519B parameters · 131.1K context · commercial OK

A.X K1 — 519B params (skt). Auto-indexed from the Hugging Face Hub (30,822 downloads). Parameter count is exact; download size and quantizations are estimates.

What it costs to run A.X K1 — $0 markup

On your own machine — $0. Runs free locally if you have about 378 GB of VRAM at Q4_K_M (point Spanvero at LM Studio, Ollama, or llama.cpp).
On your own rented GPU — from $8.34/hr. 6× NVIDIA A100 80GB at the direct RunPod price (≈ $6.97 a session), $0 markup.
Via your own API key — $4.25/1M tokens (blended input + output). No GPU to manage (rough estimate for this size).

Key facts

Parameters	519B
Context window	131.1K tokens
Recommended quant	Q4_K_M
VRAM to run	~378 GB (at Q4_K_M, 16.4K context)
Download size	~311 GB
License	Commercial use OK

Open the free Spanvero advisor → for the live, interactive math for your exact workload and hardware.

Related models

MiMo V2.5 Pro FP4 DFlash — 554.3B, XiaomiMiMo
Qwen3 Coder 480B A35B Instruct — 480.2B, Qwen
NVIDIA Nemotron 3 Ultra 550B A55B BF16 — 560.5B, nvidia
LongCat Flash Chat — 561.9B, meituan-longcat
GLM 5.2 NVFP4 — 432B, lukealonso

Browse: All models · Compare