AI Coding Live News — Real-Time 𝕏/Twitter Updates & Breakthroughs

Perplexity@perplexity_ai·Collected 50d ago

👀49

🔥91

Perplexity Portable Computer hits Windows: local agents on 24GB+ NVIDIA RTX with MCP and scheduled tasks

Perplexity says Portable Computer is now available on Windows PCs with NVIDIA RTX GPUs: run the harness, agents, and models locally, work with local files and apps, and fall back to frontier cloud models when needed. On-device work does not consume Computer credits; follow-ups add local MCP and scheduled tasks, and NVIDIA confirms 24GB+ VRAM.

Key Takeaways

Portable Computer now runs on Windows with NVIDIA RTX for local harness/agents/models.
On-device work skips Computer credits; cloud frontier models remain optional.
Adds local MCP and scheduled tasks; NVIDIA lists GeForce/RTX PRO 24GB+ VRAM.

Read full story

Linked Models & Agents:

🌐 perplexity 🌐 Nvidia (NIM)

#Perplexity#Portable Computer#Windows#NVIDIA RTX#local agents#MCP#scheduled tasks#24GB VRAM

NVIDIA RTX Spark@NVIDIARTXSpark·Collected 60d ago

👀59

🔥88

View on 𝕏 ↗

NVIDIA RTX Spark: local-agent speedups—up to 1.9× llama.cpp on RTX 5090, 1.2× vLLM on Blackwell

NVIDIA RTX Spark announced local-agent inference optimizations: up to 1.9× higher llama.cpp throughput on GeForce RTX 5090, 1.2× vLLM on RTX PRO 6000 Blackwell, and up to 1.4× on a two-system DGX Spark cluster—another step for faster on-device and local agent serving.

Key Takeaways

llama.cpp: up to ~1.9× throughput on GeForce RTX 5090 for local agent inference.
vLLM: ~1.2× on RTX PRO 6000 Blackwell; up to ~1.4× on a two-system DGX Spark cluster.
Focus: faster local/edge agent serving stacks, not only cloud inference.

Read full story

Linked Models & Agents:

#NVIDIA#RTX Spark#llama.cpp#vLLM#Blackwell#DGX Spark#local agents#Inference

Perplexity@perplexity_ai·Collected 61d ago

👀54

🔥88

View on 𝕏 ↗

Perplexity Portable Computer lands on Linux for NVIDIA RTX GPUs with 24GB+ VRAM

Perplexity (@perplexity_ai) says Portable Computer is now available on Linux for NVIDIA RTX GPUs with 24GB of VRAM or higher. It is a local-first AI assistant stack: orchestrator and subagent models can run privately on-device, with optional cloud escalation. After the earlier DGX Spark launch, this extends local deployment to consumer/workstation RTX cards.

Key Takeaways

Linux build needs NVIDIA RTX with 24GB+ VRAM.
Local-first: orchestrator LLM, subagent LLM, and agent harness can run on-device.
Complements the DGX Spark edition and lowers the bar for high-VRAM RTX workstations.

Read full story

Linked Models & Agents:

🌐 perplexity 🌐 Nvidia (NIM)

#Portable Computer#Perplexity#Linux#NVIDIA RTX#local AI#On device#Agent