Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256
Released by AgentCPT in 2026, Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 is an chat model. Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 is an open-weights chat model.
by AgentCPT
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your AgentCPT API key. osFoundry discovers Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 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
Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 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.
Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256
Is Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 free to use?
Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 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 Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 locally?
Yes. Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 best at?
Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 in osFoundry?
Paste your AgentCPT API key in the key dialog (or deploy the open weights for self-hostable models), assign Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by AgentCPT on January 7, 2026. Source: https://huggingface.co/AgentCPT/Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256