Kimi-K2.5-Pruned-340B
Built by ubicloud, Kimi-K2.5-Pruned-340B is a 340 billion parameter chat model. Kimi-K2.5-Pruned-340B is an open-weights chat model with roughly 340 billion parameters.
by ubicloud · 340B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use Kimi-K2.5-Pruned-340B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your ubicloud API key. osFoundry discovers Kimi-K2.5-Pruned-340B automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
Kimi-K2.5-Pruned-340B is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run Kimi-K2.5-Pruned-340B
Kimi-K2.5-Pruned-340B runs on a multi-GPU setup or H200 141GB at Q4 (~204 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~816 GB).
Kimi-K2.5-Pruned-340B vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Kimi-K2.5-Pruned-340B
Is Kimi-K2.5-Pruned-340B free to use?
Kimi-K2.5-Pruned-340B is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use Kimi-K2.5-Pruned-340B commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does Kimi-K2.5-Pruned-340B need?
Approximately 204 GB at Q4 quantisation, or 816 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run Kimi-K2.5-Pruned-340B locally?
Yes. Kimi-K2.5-Pruned-340B is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Kimi-K2.5-Pruned-340B best at?
Kimi-K2.5-Pruned-340B is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use Kimi-K2.5-Pruned-340B in osFoundry?
Paste your ubicloud API key in the key dialog (or deploy the open weights for self-hostable models), assign Kimi-K2.5-Pruned-340B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by ubicloud on April 3, 2026. Source: https://huggingface.co/ubicloud/Kimi-K2.5-Pruned-340B