Hackernews posts about Unsloth
- Unsloth Studio (unsloth.ai)
- Show HN: Unsloth Studio - Local Fine-tuning, Chat UI (github.com)
- Why MLX Quantized Models Underperform Unsloth GGUF (twitter.com)
- How to Run Local LLMs with Claude Code (Unsloth) (unsloth.ai)
- Claude Code makes local LLMs 90% slower (unsloth.ai)
- What are RL environments and how to build them (unsloth.ai)
- Unsloth Dynamic 2.0 GGUFs (unsloth.ai)
- Run Qwen3-Coder-480B-A35B Locally with Unsloth Dynamic Quants (docs.unsloth.ai)
- Train your own R1 reasoning model with Unsloth (unsloth.ai)
- Unsloth: GLM-4.7-Flash (unsloth.ai)
- 1.8-3.3x faster Embedding finetuning now in Unsloth (unsloth.ai)
- How to Beat Unsloth's CUDA Kernel Using Mojo–With Zero GPU Experience (www.modular.com)
- Unsloth – Train LLMs 2x faster with 70% less VRAM (github.com)
- Unsloth Dynamic GGUFs DeepSeek (671B) outperforms SOTA models (docs.unsloth.ai)
- Unsloth Dynamic 2.0 GGUFs (docs.unsloth.ai)
- Unsloth Now Supports GRPO (github.com)
- Unsloth – Dynamic 4-bit Quantization (unsloth.ai)
- Fine-Tune Llama 3.1 Ultra-Efficiently with Unsloth (huggingface.co)
- Fine-Tune Moe Models 12x Faster with Unsloth (unsloth.ai)
- Running Unsloth with all perks on DGX Spark (bartusiak.ai)
- Fine-Tuning LLMs with Nvidia DGX Spark and Unsloth (docs.unsloth.ai)
- Unsloth – Dynamic 4-bit Quantization (unsloth.ai)
- Unsloth Dynamic v.20 GGUFs (unsloth.ai)
- Finetune and Run Llama 4 with Unsloth (unsloth.ai)
- Unsloth: Dynamic 4-bit Quantization (2024) (unsloth.ai)
- Use GRPO policy locally with Qwen and Unsloth (github.com)
- Qwen3.5-35B-A3B-GGUF from Unsloth (huggingface.co)
- Train AI Models with Unsloth and Hugging Face Jobs for Free (huggingface.co)
- Unsloth: GPT-OSS (docs.unsloth.ai)
- Unsloth improvements to gguf tool calling for Qwen3 (huggingface.co)