Lemonade Server

An open-source local LLM serving tool with AMD hardware support.

ToolAI & MLllm-servingamdstrix-halo

Recommended in 1 thread

AMD expects to outsell Intel in Q4 for the first time in history
tomshardware.com · 9 days ago
A commenter cited it as a community project that AMD actively contributes to so models run better on Strix Halo.

Lemonade llama.cpp ROCm ↗AI & ML
ROCm builds of llama.cpp from the Lemonade SDK for AMD hardware.
1 thread
llm AI & ML
A command-line tool for prompting various language models.
1 thread
OpenClaw ↗AI & ML
An open personal AI assistant agent platform.
1 thread
llama-swap ↗AI & ML
A proxy that swaps between local LLM inference servers on demand.
2 threads
Inkling 2 Small ↗AI & ML
A small open-weight language model under a restrictive license.
1 thread
Claude Managed Agents ↗AI & ML
Anthropic's hosted, sandboxed agent execution service.
0 threads
Lightspeed ↗AI & ML
Open source platform for running agents in managed, governed infrastructure.
0 threads
OpenViking AI & ML
An open-source, self-hostable context and memory system for AI agents made by ByteDance.
1 thread

OpenRouter ↗
A marketplace that routes API requests to many LLM inference providers.
19 threads
DeepSeek ↗
A family of large language models offered via a low-cost API.
12 threads
llama.cpp ↗
A C/C++ engine for running LLMs locally.
12 threads
GLM ↗
An open-weights large language model family from Zhipu AI.
11 threads
Qwen ↗
Alibaba's family of open-weight large language models.
9 threads
DeepSeek V4.1 Flash ↗
A low-cost DeepSeek language model available via API.
8 threads
Artificial Analysis ↗
A site benchmarking and comparing AI models on quality, price and speed.
7 threads
Claude ↗
Anthropic's AI model and command-line assistant.
7 threads
Qwen 3.8 Flash Next ↗
A Qwen open-weight model that can be run locally.
5 threads
Strata ↗
An open-source project for running large MoE models on small-VRAM GPUs with system RAM.
5 threads
OpenCode Go ↗
A subscription plan for accessing models through the OpenCode coding tool.
4 threads
Pangram ↗
A service that uses a trained model to detect AI-generated text.
4 threads