The Curious Engineer

All blogs / AI / ML

Unsloth

unsloth.ai/blog

AI / ML

’23’24’25’26
Posts
40 from 14 Dec 2023 to 6 Oct 2026
Posting
now and then (4 in the last year)
Kind
company blog

2026 4

  1. How Unsloth Studio and Desktop Stays Secure
  2. Unsloth Joins the PyTorch Ecosystem
  3. How to Make LLM Training Faster with Unsloth and NVIDIA
  4. Reinforcement Learning environments and how to build them

2025 20

  1. gpt-oss Long Context Fine-tuning
  2. Vision Reinforcement Learning
  3. Run DeepSeek-V3.1 Locally
  4. Fine-tune gpt-oss with Unsloth
  5. Fine-tune & Run Gemma 3n with Unsloth
  6. How to Run Deepseek-R1-0528 Locally
  7. Run & Fine-tune Qwen3
  8. Fine-tune TTS models with Unsloth
  9. Unsloth Dynamic v2.0 GGUFs
  10. Llama 4 - Finetune & Run with Unsloth
  11. How to Run Deepseek-V3-0324 Locally
  12. Fine-tune Mistral Small 3.1 with Unsloth
  13. Fine-tune Gemma 3 with Unsloth
  14. Run & Finetune QwQ-32B with Bug Fixes
  15. Long-context GRPO (R1 Reasoning)
  16. Re-introducing Unsloth
  17. Train your own R1 reasoning model locally (GRPO)
  18. Run DeepSeek-R1 Dynamic 1.58-bit
  19. Run Deepseek-R1 / R1 Zero
  20. Finetune Phi-4 with Unsloth

2024 15

  1. Fine-tune Llama 3.3 with Unsloth
  2. Unsloth - Dynamic 4-bit Quantization
  3. Llama 3.2 Vision Fine-tuning with Unsloth
  4. Qwen 2.5 Coder Fine-tuning with Unsloth
  5. Bug Fixes in LLM Training - Gradient Accumulation
  6. Fine-tune Llama 3.2 Vision with Unsloth
  7. Finetune Llama 3.1 with Unsloth
  8. Finetune Mistral NeMo with Unsloth
  9. Finetune Gemma 2 with Unsloth
  10. Continued LLM Pretraining with Unsloth
  11. Finetune Phi-3 with Unsloth
  12. Finetune Llama 3 with Unsloth
  13. Unsloth Gradient Checkpointing - 4x longer context windows
  14. Unsloth Fixing Gemma bugs
  15. Finetune Gemma with Unsloth

2023 1

  1. Unsloth update: Mistral support + more