Kimi K2.5 / K2.6 / K2.7 — Local AI Model by Moonshot AI

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 15 sierpnia 2026

Przełom Moonshot AI z lutego 2026. Kimi K2.5 ma 1 bilion parametrów (32B aktywnych, 384 ekspertów) i osiągnął najwyższy wynik w historii HumanEval: 99,0. Wytrenowany na 15 bilionach tokenów wizyjnych i tekstowych od podstaw — wizja to kluczowa funkcja, nie dodatek.

Licence

Licence	What it permits	Applies to
`Kimi Research`	Research / non-commercial only Research / non-commercial only — this licence does NOT permit shipping a commercial product.	Kimi K2.5, Kimi K2.6
`Custom Open-Weight`	Commercial use permitted Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.	Kimi K2.5 1T (32B Active)
`Modified MIT`	Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution.	Kimi K2.7 Code

Hardware Requirements

Kimi K2.5	Min 20 GB VRAM · Q4_K_M · 128,000 ctx · `ollama run hf.co/moonshotai/Kimi-K2.5-Instruct-Q4_K_M`
Kimi K2.6	Min 20 GB VRAM · Q4_K_M · 128,000 ctx · `ollama run hf.co/moonshotai/Kimi-K2.6-Instruct-Q4_K_M`
Kimi K2.5 1T (32B Active)	Min 605 GB VRAM · Q4_K_M · 200,000 ctx · `ollama run hf.co/moonshotai/Kimi-K2.5`
Kimi K2.7 Code	Min 605 GB VRAM · INT4 (native) · 262,144 ctx ·

Recommended GPU

The cheapest GPU that runs Kimi K2.5 / K2.6 / K2.7 locally (min 20 GB VRAM) is the AMD Radeon RX 7900 XT (20 GB).

Ujawnienie afiliacyjne: Niektóre odnośniki na tej stronie to linki afiliacyjne — jeśli dokonasz zakupu za ich pośrednictwem, LLM Configurator może otrzymać prowizję bez dodatkowych kosztów dla Ciebie. Jako uczestnik programu Amazon Associates, LLM Configurator zarabia na kwalifikujących się zakupach.

AMD Radeon RX 7900 XT 20GB

20 GB VRAM · 315 W board power

Ceny w 2026 są niestabilne — sprawdź aktualną ofertę.

Sprawdź cenę na Amazon

How to Run Locally

Install Ollama then run: ollama run hf.co/moonshotai/Kimi-K2.5-Instruct-Q4_K_M

Minimum VRAM: 20 GB. For best results use Q4_K_M quantization.

Kimi K2.5 / K2.6 / K2.7 — Frequently Asked Questions

How much VRAM does Kimi K2.5 / K2.6 / K2.7 need?

Kimi K2.5 / K2.6 / K2.7 needs about 20 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Kimi K2.5 (20 GB, Q4_K_M); Kimi K2.6 (20 GB, Q4_K_M); Kimi K2.5 1T (32B Active) (605 GB, Q4_K_M); Kimi K2.7 Code (605 GB, INT4 (native)). On Apple Silicon, unified memory counts toward this requirement.

Can I run Kimi K2.5 / K2.6 / K2.7 on an RTX 4090 (24 GB)?

Yes — Kimi K2.5 / K2.6 / K2.7 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for Kimi K2.5 / K2.6 / K2.7?

Q4_K_M is the best balance of quality and VRAM for Kimi K2.5 / K2.6 / K2.7 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run Kimi K2.5 / K2.6 / K2.7 with Ollama?

Install Ollama, then run: ollama run hf.co/moonshotai/Kimi-K2.5-Instruct-Q4_K_M. This downloads Kimi K2.5 / K2.6 / K2.7 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.