#INT8 quantization
748 related articles
·3 min
persistent-inference: Solving TF/Keras Cold Start Problems with Just Two Files
Deep dive into the persistent-inference open-source project: solve TF/Keras cold start problems with just two files by keeping models resident in memory, eliminating reload overhead.
Read more →
·4 min
Mistral Shieldstral: A Deep Dive into the 3B Parameter Open-Source Multimodal Content Moderation Model
Mistral releases Shieldstral, an open-source multimodal content moderation model with just 3B parameters for text and image safety detection. Learn about its features, use cases, and comparison with Llama Guard.
Read more →
·3 min
Poolside Desktop Assistant 1.4.0 Update: Subagent Collaboration and Local Model Speed Boost
Poolside Desktop Assistant 1.4.0 adds native steering, task queuing, plan mode, and subagent collaboration, plus major local model inference speed improvements with deep Claude and Codex integration.
Read more →
·3 min
Running a Small Language Model on an $8 Chip: Pushing the ESP32-S3 to Its Limits
Exploring training and running a small language model (SLM) on an ESP32-S3 microcontroller costing just $8. Learn about model design under extreme hardware constraints, quantization strategies, and edge AI's potential.
Read more →
·3 min
Running a Local AI Voice Assistant on a $50 Arduino Board: A Practical Guide to Edge AI
How to run a fully local AI voice agent on a $50 Arduino Uno Q board, covering speech recognition, intent understanding, and TTS implementation for edge AI applications.
Read more →
·3 min
Maple-Preview: 20B Ternary MoE Model Achieves 120 tok/s On-Device Inference on iPhone
Maple-Preview achieves 120 tok/s inference of a 20B ternary MoE model on iPhone. We analyze ternary quantization, MoE sparse activation, and on-device inference challenges.
Read more →
·3 min
From DevOps to MLOps: Market Demand, Transition Path, and Practical Advice
In-depth analysis of transitioning from DevOps to MLOps: core differences, market demand, required skills, and a practical three-step path for operations engineers making rational career decisions.
Read more →
·3 min
Training ASR Models with Simulated Call Center Audio: Can the Gap Between Simulated and Real Data Be Bridged?
Deep dive into training ASR models with simulated call center audio: analyzing codec simulation, code-switching, and diarization bottlenecks that reveal the gap between simulated and real phone data.
Read more →
·3 min
The 5-Layer AI Tech Stack Explained: A Complete Industry Chain from Energy to Applications
Deep dive into the 5-layer AI tech stack: Energy, Chips, Infrastructure, Models, and Applications. Understand the key players, competitive landscape, and value distribution logic across the AI industry chain.
Read more →
·3 min
Quantprobe: An Open-Source Tool for Running 30B LLMs on 6GB GPUs
Quantprobe is an open-source memory optimization framework that enables 30B LLMs to run at 22 tokens/s on 6GB GPUs through per-layer quantization and intelligent CPU/GPU splitting.
Read more →
·3 min
Fine-Tuning 8B LLMs on a 4GB GPU: A Deep Dive into VRAM Optimization Techniques
Learn how to fine-tune 8B parameter LLMs on a 4GB laptop GPU using QLoRA quantization, gradient checkpointing, and gradient accumulation VRAM optimization techniques.
Read more →
·2 min
$100 Million Deal: AI Gives 50,000 Ukrainian Kamikaze Drones Autonomous Target Lock
A U.S. company struck a $100M deal with Ukraine to deploy AI visual lock-on capabilities on 50,000 cheap kamikaze drones, enabling terminal autonomous guidance to defeat electronic warfare jamming.
Read more →
·2 min
Qwen3.8-Max Preview Continues Iterating with Major Improvements in Frontend Development Capabilities
Alibaba's Qwen3.8-Max-Preview iterates daily with significant frontend development improvements. The team uses an open preview strategy to collect community feedback, promising open-weight release.
Read more →
·2 min
H3 Voice Model Full-Precision Weights Released: Impressive Expressiveness but Long-Sentence Voice Drift Remains Unsolved
H3 voice model releases full-precision weights. Community tests show strong expressiveness, voice cloning, and multilingual support, but voice drift in long sentences and imprecise stress remain.
Read more →
·4 min
Running an 80B Large Model on Mac with Only 4.3GB of Memory: Extreme Compression Techniques Explained
Deep dive into how an 80B-parameter LLM runs on Mac with only 4.3GB memory, covering ultra-low-bit quantization, sparsity, memory mapping, and implications for privacy and edge AI.
Read more →
·3 min
Open Source Wins: How China Is Using Open Source Strategy to Dominate the Second Half of AI
Chinese open-source AI models are rapidly rising with near-top performance at fraction of cost, dominating local deployment. As the gap shrinks to single digits and OpenAI cuts prices, open source is reshaping AI competition.
Read more →
·3 min
Nightcrawler: Deep Dive into an AI Penetration Testing Agent Running Locally on Smartphones
Deep analysis of Nightcrawler, an AI penetration testing agent running entirely on smartphones. Exploring how on-device AI empowers cybersecurity testing, its architecture, use cases, and risks.
Read more →
·2 min
yapyap: A Local-First Open-Source Meeting Recording and Transcription Tool
yapyap is a local-first open-source meeting recording tool supporting transcription, speaker diarization, and AI summaries—all running locally with no cloud uploads or subscriptions required.
Read more →
·3 min
PISIGuard: Protecting Your Privacy When Chatting with AI
PISIGuard is an open-source privacy tool that automatically detects and anonymizes names, phone numbers, and IDs before they reach AI chatbots like ChatGPT, preventing personal data leaks to cloud servers.
Read more →
·3 min
Hand Wave: Real-Time Sign Language Translation on Meta Smart Glasses for Barrier-Free Communication
Hand Wave uses Meta smart glasses' camera and open-source AI neural networks to translate sign language into text and speech in real time, supporting iOS and Web platforms.
Read more →