Featured Tool

QLoRA

Efficient fine-tuning method using 4-bit quantized base model with LoRA adapters.

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

About

QLoRA from the University of Washington is an efficient fine-tuning method that backpropagates gradients through a frozen 4-bit quantized model into LoRA adapters, letting a 65B parameter model be fine-tuned on a single 48 GB GPU while preserving 16-bit fine-tuning quality. It uses 4-bit NormalFloat quantization via bitsandbytes and integrates with Hugging Face PEFT and Transformers. Released under the MIT license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Intermediate (3/5)
License
MIT
Minimum VRAM
8 GB
Added
Apr 3, 2026

Related Tools

Efficient LLM quantization preserving important weight channels.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

Video model fine-tuning toolkit by Hugging Face Diffusers team.

Open SourceSelf HostedOfflineGPU 16GB+
Advanced
0.0 (0)

Low-code framework for building custom AI models by Predibase.

Open SourceSelf HostedOfflineGPU 8GB+
Easy
0.0 (0)
Featured

Library for training LLMs with reinforcement learning (RLHF, DPO, PPO).

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Featured

All-in-one framework for fine-tuning 100+ LLMs with web UI.

Open SourceSelf HostedOfflineGPU 8GB+
Easy
0.0 (0)

No-code tool by Hugging Face for training ML models automatically.

Open SourceSelf HostedOfflineGPU 8GB+
Beginner
0.0 (0)
Browse all Model Training & Fine-Tuning tools