Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT
Released by Thireus in 2026, Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT is a 397 billion parameter chat model. Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT is an open-weights chat model with roughly 397 billion parameters.
by Thireus · 397B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Thireus API key. osFoundry discovers Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT 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
Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT 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 Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT
Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT runs on a multi-GPU setup or H200 141GB at Q4 (~239 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~953 GB).
Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT
Is Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT free to use?
Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT 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 Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT 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 Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT need?
Approximately 239 GB at Q4 quantisation, or 953 GB at full FP16 precision. Requires multi-GPU at higher quantisation.
Can I run Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT locally?
Yes. Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT best at?
Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT in osFoundry?
Paste your Thireus API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Thireus on April 25, 2026. Source: https://huggingface.co/Thireus/Qwen3.5-397B-A17B-THIREUS-IQ2_KT-SPECIAL_SPLIT