KTransformers

Heterogeneous CPU and GPU inference framework for very large language models on limited hardware.

Open SourceSelf HostedOffline CapableGPU Required (24GB+ VRAM)
0.0 (0)

About

KTransformers is a research framework for efficient CPU and GPU heterogeneous inference and fine-tuning of large language models. It includes a kt-kernel serving stack with AMX and AVX acceleration, MoE optimizations, and quantization support. The project integrates with LLaMA-Factory for fine-tuning ultra-large MoE models on constrained hardware.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Advanced (4/5)
License
Apache-2.0
Minimum VRAM
24 GB
Added
May 7, 2026

Related Tools

Featured

Port of Meta's LLaMA model in C/C++ for efficient CPU inference

Open SourceSelf HostedOffline
Intermediate
0.0 (0)
Featured

High-throughput LLM serving engine with PagedAttention

Open SourceSelf HostedOfflineGPU 16GB+
Intermediate
0.0 (0)

Minimalist ML framework in Rust by Hugging Face for fast inference.

Open SourceSelf HostedOffline
Advanced
0.0 (0)

Optimized inference library for running quantized LLMs on consumer GPUs.

Open SourceSelf HostedOfflineGPU 6GB+
Intermediate
0.0 (0)

Open-source ChatGPT alternative that runs 100% offline on your computer.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

Fast LLM inference on consumer GPUs using neuron-aware sparse computation.

Open SourceSelf HostedOfflineGPU 4GB+
Advanced
0.0 (0)
Browse all LLM Inference & Serving tools