Unsloth
2 published articles
AIFeatured3 min read
Training optimization
Unsloth's new kernels just made LLM fine-tuning 5x faster, no VRAM overpay
Unsloth's latest update introduces fused QK RoPE Triton kernels for 2.3x faster rotary embeddings, int64 indexing for long context, and auto padding-free packing. Benchmarks show 1.7-3x faster throughput on Qwen3-32B with no accuracy loss.
2026-07-16
Open Source3 min read
Model Quantization
Inkling was a 1.9 TB model. Unsloth just squeezed it into a desktop.
Unsloth's dynamic GGUF quantization shrinks Inkling, a 975B-parameter open model, from 1.9 TB to 270 GB at 1-bit with 74.2% accuracy retention. The method selectively preserves high-precision layers, enabling local inference on machines with 290 GB of combined RAM and VRAM.
2026-07-16