Qwen3.5-122B-A10B-NVFP4-resharded
Qwen3.5-122B-A10B-NVFP4-resharded is a 122 billion parameter chat model from sjug, released March 23, 2026. Qwen3.5-122B-A10B-NVFP4-resharded is an open-weights chat model with roughly 122 billion parameters.
by sjug · 122B parameters
Best for
- complex multi-step reasoning
- agent orchestration with tool use
- long-document analysis and summarisation
Ways to use Qwen3.5-122B-A10B-NVFP4-resharded in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your sjug API key. osFoundry discovers Qwen3.5-122B-A10B-NVFP4-resharded 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
Qwen3.5-122B-A10B-NVFP4-resharded 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 Qwen3.5-122B-A10B-NVFP4-resharded
Qwen3.5-122B-A10B-NVFP4-resharded runs on a single A100 80GB or H100 80GB at Q4 quantisation (~74 GB VRAM with KV-cache headroom). Full-precision inference requires multiple H100/H200 GPUs at FP16 (~293 GB).
Qwen3.5-122B-A10B-NVFP4-resharded vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen3.5-122B-A10B-NVFP4-resharded
Is Qwen3.5-122B-A10B-NVFP4-resharded free to use?
Qwen3.5-122B-A10B-NVFP4-resharded 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 Qwen3.5-122B-A10B-NVFP4-resharded 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 Qwen3.5-122B-A10B-NVFP4-resharded need?
Approximately 74 GB at Q4 quantisation, or 293 GB at full FP16 precision. Fits on a single A100/H100 80GB.
Can I run Qwen3.5-122B-A10B-NVFP4-resharded locally?
Yes. Qwen3.5-122B-A10B-NVFP4-resharded is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen3.5-122B-A10B-NVFP4-resharded best at?
Qwen3.5-122B-A10B-NVFP4-resharded is well-suited to complex multi-step reasoning, agent orchestration with tool use, long-document analysis and summarisation.
How do I use Qwen3.5-122B-A10B-NVFP4-resharded in osFoundry?
Paste your sjug API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen3.5-122B-A10B-NVFP4-resharded to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by sjug on March 23, 2026. Source: https://huggingface.co/sjug/Qwen3.5-122B-A10B-NVFP4-resharded