DEV Community

#localai

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Meet hope-agent: The Rust-Powered Autonomous Desktop & Headless AI Assistant

Meet hope-agent: The Rust-Powered Autonomous Desktop & Headless AI Assistant

Comments
2 min read
NVFP4 Won't Save Your VRAM: Quantization Tradeoffs on a 12GB Laptop GPU

NVFP4 Won't Save Your VRAM: Quantization Tradeoffs on a 12GB Laptop GPU

Comments
3 min read
[Phân tích kỹ thuật] NVIDIA Mở Bán RTX Spark: Máy Tính Để Bàn Nhỏ Gọn 1 Petaflop, Đưa AI Agent Và Blackwell Về Bàn Làm Việc

[Phân tích kỹ thuật] NVIDIA Mở Bán RTX Spark: Máy Tính Để Bàn Nhỏ Gọn 1 Petaflop, Đưa AI Agent Và Blackwell Về Bàn Làm Việc

Comments
10 min read
Скачал полтерабайта локальных LLM — но без GPU жизни нет

Скачал полтерабайта локальных LLM — но без GPU жизни нет

Comments
12 min read
Local AI on a PC: what actually works (Whisper, translation, LLMs)

Local AI on a PC: what actually works (Whisper, translation, LLMs)

1
Comments
2 min read
Unsloth Dynamic V3.1: Qwen3.8-27B Local Agent Benchmarks

Unsloth Dynamic V3.1: Qwen3.8-27B Local Agent Benchmarks

Comments
1 min read
Faire tourner un MoE de 35B sur une GTX 1650 4 Go : le test réel

Faire tourner un MoE de 35B sur une GTX 1650 4 Go : le test réel

Comments
7 min read
Hybrid AI setups seem to be most practical setup right now compared to fully local (for certain workflows)

Hybrid AI setups seem to be most practical setup right now compared to fully local (for certain workflows)

2
Comments 2
2 min read
Local AI Development with the Surface Laptop Ultra

Local AI Development with the Surface Laptop Ultra

Comments
42 min read
datasette-llm 0.1a11:通过 OpenAI 兼容接口接入本地模型

datasette-llm 0.1a11:通过 OpenAI 兼容接口接入本地模型

Comments 1
1 min read
Klepai v0.1.0: regenerate keeps your old answer

Klepai v0.1.0: regenerate keeps your old answer

Comments
3 min read
How I Run a 27B Local Agent on a 12GB Laptop GPU: KVMem, Tiered KV, and Honest Long-Context Limits

How I Run a 27B Local Agent on a 12GB Laptop GPU: KVMem, Tiered KV, and Honest Long-Context Limits

Comments 1
6 min read
llama.cpp 1.0.0 Stabilizes the Local Inference API — Dual-Track WASAPI Capture Still Owns the Latency Budget

llama.cpp 1.0.0 Stabilizes the Local Inference API — Dual-Track WASAPI Capture Still Owns the Latency Budget

Comments
4 min read
Running Mano-P on the Cheapest Mac It Survives On

Running Mano-P on the Cheapest Mac It Survives On

1
Comments
3 min read
Speech Studio 0.5.0 Drops Local Multi-Engine TTS+STT on Windows — First-Sound Latency Still Sets the Overlay Floor

Speech Studio 0.5.0 Drops Local Multi-Engine TTS+STT on Windows — First-Sound Latency Still Sets the Overlay Floor

Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.