kimi-k3-b300x8-k3turbo
Published Jul 31, 2026. Proof verified Jul 31, 2026.
2.12x faster
Median latency measured 19090 ms at baseline and 8978 ms optimized.
Quality evidence
Parity by construction.
Model
Kimi K3 measured packages and prices
RunInfra has published 1 measured package for moonshotai/Kimi-K3 on B300. Every package below keeps its engine, price, and proof date together.
The published packages are available to buy
| Package | GPU | Engine | Optimization | Price | Verified |
|---|---|---|---|---|---|
| kimi-k3-b300x8-k3turbo | B300 | vLLM 0.23.1 | Optimization technique not published. | $100 one-time | Jul 31, 2026 |
What we measured
The package keeps the upstream weights unchanged and sells the validated serving profiles, build recipe, and proof instead.
Published package measurements and prices for Kimi K3, grouped from the public RunInfra catalog.
Measured by RunInfra on B300 with vLLM 0.23.1; proof dates are listed with each package.
We report package measurements here, and each package remains subject to its listed license.
Citation: RunInfra (2026). Measured open-model serving benchmarks. https://runinfra.ai/catalog.
What is not measured
Other GPU measurements for this model not published.
Other engine measurements for this model not published.
Measurements for context lengths not listed in these packages not published.
Published facts answer common questions
What does Kimi K3 cost on RunInfra?
kimi-k3-b300x8-k3turbo is listed at $100 one-time, published Jul 31, 2026.
Which GPU serves Kimi K3?
kimi-k3-b300x8-k3turbo is measured on B300 with vLLM 0.23.1. Proof verified Jul 31, 2026.
Is quality measured for Kimi K3?
Parity by construction. Proof verified Jul 31, 2026.
If you need custom optimization for a specific model, describe what you need
End-to-end encryption
Isolated GPU infrastructure
No training on your data
SOC 2 Type II
RunInfraby RightNow© 2026 RunInfra. All rights reserved.
Ask AI about RunInfra
