# #llms — MDRSS hashtag feed

> Public MDRSS cards tagged #llms.
> Canonical feed: https://mdrss.com/feeds/llms

## Cards (7)

### [LLMTools: Run & Finetune LLMs on Consumer GPUs](https://mdrss.com/llm-engineering/inference-and-quantization/901083/901083.md)

LLMTools is a user-friendly library for running and finetuning LLMs in low-resource settings. Features include: 🔨 LLM finetuning in 2-bit, 3-bit, 4-bit precision using the ModuLoRA algorithm 🐍 Easy-to-use Python API for quantization, inference, and finetuning 🤖 Modular supp. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [AI Hedge Fund](https://mdrss.com/learning/curricula-and-careers/2050/2050.md)

This is a proof of concept for an AI-powered hedge fund. The goal of this project is to explore the use of AI to make trading decisions.

Classification: learning/curricula-and-careers · Feed: learning · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [ChainForge](https://mdrss.com/ai-agents/prompting/2004/2004.md)

An open-source visual environment for battle-testing prompts to LLMs. ChainForge is a data flow prompt engineering environment for analyzing and evaluating LLM responses.

Classification: ai-agents/prompting · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [QLoRA: Efficient Finetuning of Quantized LLMs](https://mdrss.com/llm-engineering/serving-and-retrieval/1671/1671.md)

This repo supports the paper "QLoRA: Efficient Finetuning of Quantized LLMs", an effort to democratize access to LLM research. QLoRA uses bitsandbytes for quantization and is integrated with Hugging Face's PEFT and transformers libraries.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [News](https://mdrss.com/ai-agents/prompting/1415/1415.md)

This approach enables efficient inference with large language models (LLMs), achieving up to 20x compression with minimal performance loss. Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang and Lili Qiu LongLLMLingua mitigates the 'lost in the middle' issue in LLMs, enhancing long-context information processing.

Classification: ai-agents/prompting · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [nanobot](https://mdrss.com/ai-agents/agent-frameworks/1160/1160.md)

English | 简体中文 | 繁體中文 | Español | Français | Bahasa Indonesia | 日本語 | 한국어 | Русский | Tiếng Việt Discord · X · WeChat / Feishu 🐈 nanobot is an ultra-lightweight, open-source, self-hosted personal AI agent framework written in Python. It runs in a WebUI, terminal, or chat apps and combines tools, long-term memory, MCP integrations, model routing, multi-agent delegation, scheduled automation, and an OpenAI-compatible API in a small, readable core.

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Lobster](https://mdrss.com/software-craft/developer-tooling/888/888.md)

An OpenClaw-native workflow shell: typed (JSON-first) pipelines, jobs, and approval gates. OpenClaw (or any other AI agent) can use lobster as a workflow engine and avoid re-planning every step — saving tokens while improving determinism and resumability.

Classification: software-craft/developer-tooling · Feed: software-craft · Updated: 2026-08-04T12:22:38.168Z · Version: 1