DEV Community

#localai

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
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
Kindi – fast local inference on low-cost GPUs, and the exact-match rule that makes its numbers trustworthy

Kindi – fast local inference on low-cost GPUs, and the exact-match rule that makes its numbers trustworthy

Comments
7 min read
Project Maya – four huge MoE models on the GPUs you already own, each with its own engine

Project Maya – four huge MoE models on the GPUs you already own, each with its own engine

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

Klepai v0.1.0: regenerate keeps your old answer

Comments
3 min read
What Is the Best App to Run AI Models Offline on Your Phone? (iPhone and Android, 2026)

What Is the Best App to Run AI Models Offline on Your Phone? (iPhone and Android, 2026)

Comments
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
One gaming PC, one 552B MoE: how expert offload actually works

One gaming PC, one 552B MoE: how expert offload actually works

Comments
4 min read
Hot experts, cold RAM: a big MoE on a box with more memory than VRAM

Hot experts, cold RAM: a big MoE on a box with more memory than VRAM

Comments
3 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
MCP servers, and what they let a local model actually do: Blender, CADCraft and the DWG problem

MCP servers, and what they let a local model actually do: Blender, CADCraft and the DWG problem

Comments
17 min read
How to make a local AI model give the same answer every time

How to make a local AI model give the same answer every time

Comments
3 min read
My Go-To Prompt for Testing Local LLMs

My Go-To Prompt for Testing Local LLMs

Comments
1 min read
Apiiro’s Claude Code Scan Found 2,539 Secrets in .claude/settings.local.json — Local Desktop Tools Keep Credentials Off the Git Path

Apiiro’s Claude Code Scan Found 2,539 Secrets in .claude/settings.local.json — Local Desktop Tools Keep Credentials Off the Git Path

Comments
3 min read
Hugging Face’s 70k-Word MoE Handbook After 800k GPU Hours — Why Sparsity Still Wins for Local Real-Time Tools

Hugging Face’s 70k-Word MoE Handbook After 800k GPU Hours — Why Sparsity Still Wins for Local Real-Time Tools

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