Boost 2-Bit LLM Accuracy with EoRA

LoRA at Scale on a Consumer GPU: Does It Work?

Fine-Tuning Qwen3: Base vs. Reasoning Models

Accurate 2-bit Quantization: Run Massive LLMs on a Single Consumer GPU

Make LLMs Faster and Lighter with W8A8 Quantization

Run Llama 3.3 70B on Your GPU with ExLlamaV3

Fast and Memory-Efficient Full Fine-Tuning with Unsloth (single-GPU)

Llama 4 with 10M Tokens: How Much Does It Cost and Is It Worth It?

LoRA Trainable Tokens: Save Memory, Improve Accuracy for Your Domain

BF16 vs. FP16 vs. FP32 for Gemma 3 Inference — Mind Your Data Type

Fine-Tuning Gemma 3 on Your Computer with LoRA and QLoRA (+model review)

TransMLA: Improve Qwen2.5 and Llama 3x LLMs with DeepSeek's Multi-Head Latent Attention