What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Embabel can stream LLM output as it arrives, including raw text, thinking events and generated objects. For agent workflows, its streaming tool loop can also execute requested tools between model inference turns while continuing to send events to your application. The current Embabel Agent Framework User Guide, version 1.5.1, documents the APIs and their limits.
What Embabel streaming sends to your application
Streaming lets an application receive LLM output incrementally rather than waiting for an entire response. In Embabel, the stream can carry raw text, thinking content, or generated objects. The event types matter: code that consumes object streams should inspect the event and handle thinking and parsed objects separately, rather than assuming every event is the final result.
The guide documents StreamingEvent, StreamingPromptRunnerBuilder, LlmMessageStreamer, and StreamingToolLoop, including its default implementation, DefaultStreamingToolLoop. The stream is reactive, so handlers such as doOnNext, doOnError, and doOnComplete can process incoming values, report failures, and respond to completion.
Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Repair Windows errors before they cause bigger problemsFix Now →How to create a basic text stream
The current guide’s raw-text example builds a streaming prompt runner, supplies a prompt, and calls generateStream() to obtain a Flux<String>. Attach reactive handlers to consume chunks and handle the stream lifecycle.
#1 Best Overall
- EVOLUTION AMD RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 128GB pool, which is perfect for running LLMs such as Deepseek 70B Q8, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 12% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
- Create a streaming runner with
StreamingPromptRunnerBuilderand.streaming(). - Set the prompt with
.withPrompt(prompt). - Call
.generateStream()to produce the text stream. - Subscribe or attach reactive operators, including
doOnNext,doOnError, anddoOnComplete, as appropriate for the application.
Use the API spelling from the guide that matches your Embabel dependency. The older 0.3.1 guide uses .withStreaming(); the current 1.5.1 guide shows .streaming(). Examples from different releases should not be combined without checking the versioned documentation.
How to stream generated objects
For structured output, select a target type that gives the model an object schema. Embabel’s object-stream handling distinguishes parsed object events from thinking events, so consumers should branch on event type and process each appropriately.
Rank #2
- Built for Local AI Development: AMD Ryzen AI Halo is designed for local AI development and inference, featuring 128GB unified memory and support for up to 200B parameter models to build and run intensive AI workloads locally.
- 128GB Unified Memory: Features 128GB LPDDR5x unified memory at 8000 MT/s with 256 GB/s memory bandwidth, providing a shared memory pool across the CPU, GPU, and NPU to support larger AI models.
- AMD Ryzen AI Max+ 395 Processor: Features 16 cores, 32 threads, and Zen 5 architecture, paired with AMD Radeon 8060S integrated graphics featuring 40 RDNA 3.5 compute units and an AMD XDNA 2 NPU with up to 50 TOPS.
- Linux AI Developer Platform: Purpose-built for Linux-based AI development with full AMD ROCm software support and preloaded tools, models, and workflows optimized for local AI development.
- Compact, Connected Design: Includes a 2TB M.2 SSD, 10GbE LAN, Wi-Fi 7, Bluetooth 5.4, USB-C connectivity, and HDMI 2.1b.
Wrap scalar strings in an object
The current guide cautions against using String.class directly for structured streaming: bare JSON strings can be mistaken for thinking content by the structured streaming parser. Instead, wrap the scalar in a type such as StringResult. The model can then return an object with a value property, which the stream can emit as a structured object event.
Free tools Windows power users keep installed
One-click scans. No signup required.
How streaming works with tools
LlmMessageStreamer.streamInference advertises the available tools and streams one model inference. It does not execute tools itself. The streaming tool loop coordinates the larger interaction: it assembles the assistant response, executes requested tools, adds tool outputs to the conversation, and starts another inference. The returned stream includes content from each inference turn, including thinking content emitted before or between tool calls.
Rank #3
- EVOLUTION RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 128GB pool, which is perfect for running LLMs such as Deepseek 70B Q8, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 12% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
This means streaming and tool execution are related but distinct responsibilities. Your application receives intermediate events while Embabel manages the cycle of model inference and requested tool calls. The tools available can also change between turns; the guide identifies ToolInjectionStrategy and UnfoldingToolInjectionStrategy as ways to manage tool availability.
What to verify before relying on structured streaming
The current guide states that Spring AI does not currently support native structured output for streaming. That limitation concerns the native structured-output path; it does not mean Embabel cannot stream raw text or expose object-stream APIs. Confirm behavior with the specific Embabel release, Spring AI integration, and provider used by your application. The guide’s historical implementation discussion includes OpenAI, Anthropic, and Ollama integration-test examples, but it is not a guarantee that every provider and version combination behaves identically.
How Embabel relates to Spring AI
Embabel is a JVM framework built on Spring AI. Spring AI supplies underlying model integrations, while Embabel provides a higher-level layer for agent workflows, composable actions, orchestration, and testing. The practical choice depends on the shape of the application: direct Spring AI may suit an application that only needs model calls, while Embabel provides workflow and tool-loop structure for agent interactions. These are different abstraction levels, not evidence of a general speed, cost, or output-quality advantage.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
