Unsloth Blog
23 posts indexed since 2025
Post Details
| Title | Author | Published | Words | HN Pts |
|---|---|---|---|---|
| Phi-4 Finetuning + Bug Fixes by Unsloth | Daniel & Michael | 2025-01-10 | 796 | -- |
| Fine-tune & Run Mistral Small 3.1 | Daniel & Michael | 2025-03-17 | 434 | -- |
| Vision Reinforcement Learning | Daniel & Michael | 2025-08-28 | 918 | -- |
| Run & Finetune DeepSeek-R1 | Daniel & Michael | 2025-01-20 | 889 | -- |
| Train your own R1 reasoning model with Unsloth (GRPO) | Daniel & Michael | 2025-02-06 | 1,478 | -- |
| Fine-tune & Run Gemma 3 | Daniel & Michael | 2025-03-14 | 1,482 | -- |
| Long-context GRPO | Daniel & Michael | 2025-02-20 | 1,863 | -- |
| Re-introducing Unsloth | Daniel & Michael | 2025-02-10 | 714 | -- |
| Fine-tune gpt-oss with Unsloth | Daniel & Michael | 2025-08-08 | 1,182 | -- |
| Run DeepSeek-R1-0528 Dynamic 1-bit GGUFs | Daniel & Michael | 2025-05-29 | 1,380 | -- |
| Run DeepSeek-V3-0324 | Daniel & Michael | 2025-03-25 | 1,234 | -- |
| Run DeepSeek R1Dynamic 1.58-bit | Daniel & Michael | 2025-01-27 | 2,359 | -- |
| Fine-tune & Run Gemma 3n | Daniel & Michael | 2025-07-01 | 1,368 | -- |
| Run QwQ-32B effectively + Bug Fixes | Daniel & Michael | 2025-03-07 | 2,207 | -- |
| Run DeepSeek-V3.1 Dynamic 1-bit GGUFs | Daniel & Michael | 2025-08-21 | 961 | -- |
| Unsloth Dynamic 2.0 GGUFs | Daniel & Michael | 2025-04-24 | 1,408 | -- |
| Long context gpt-oss Fine-tuning | Daniel & Michael | 2025-08-28 | 1,661 | -- |
| Fine-tune & Run Qwen3 | Daniel & Michael | 2025-05-02 | 430 | -- |
| Fine-tuning TTS models | Daniel & Michael | 2025-05-02 | 416 | -- |
| Fine-tune & Run Llama 4 | Daniel & Michael | 2025-04-07 | 471 | -- |
| What are RL environments and how to build them | -- | 2026-03-12 | 3,289 | -- |
| Unsloth collaborates with NVIDIA to make training faster | -- | 2026-03-13 | 2,589 | -- |
| Unsloth Joins PyTorch Ecosystem | Daniel & Michael | 2026-05-11 | 953 | -- |