RTX 4090

24 GB · single-card node · $2,999 Card · $4,199 Full rig

Quick decision verdict

RTX 4090 outputs 109.3 tok/s at $0.056/M tokens (rank #1 of 28 measured rigs on unit cost), breaking even in 434 days at full load.

  • Generation speed rank #4 of 29 · System power rank #23 (550 W).
  • For a lower upfront build cost, compare against RTX 5080 ($2,800)
  • If you need faster interactive token speed, compare against RTX PRO 6000 Blackwell (171.1 tok/s)

Can I Run It? → · Best → · Method →

How you'll use it

Fits?Source
RTX 4090
single-card node
24 GB4,000109.3Roomy550 W$4,19975.8$0.056$1.98$11.67433 daysMeasured

Selected hardware

RTX 4090

24 GB · single-card node

Read tok/s
4,000
Write tok/s
109.3
Power
550 W
Output/day
75.8
Cost/M tok
$0.056
Power/day
$1.98
Saved/day
$11.67
Payback
433 days

Details · See source

FAQ

How fast does RTX 4090 run local LLMs?
RTX 4090 (24 GB) measures 109.3 tokens/s generation and 4,000 tokens/s prompt reading on Qwen3.8-Flash-Next (snapshot 2026-10-07).
Is RTX 4090 worth buying over cloud LLM APIs?
At $0.056/M tokens local cost, RTX 4090 breaks even in 434 days at 24h/day utilization, or 2,599 days at 4h/day — making daily utilization the main deciding factor.