Home / Companies / Unsloth / Hacker News

Unsloth on HN

35 posts with 1+ points since 2023

Filters
Since:
Posts by Month (35 total)
Hacker News Posts
Title Points Comments Date
Run DeepSeek R1 Dynamic 1.58-bit 767 -- 2025-01-28
Fine-tune Google's Gemma 3 226 -- 2025-03-19
Phi-4 Bug Fixes 193 -- 2025-01-10
GPT-OSS Reinforcement Learning 180 -- 2025-09-27
Fixing Gemma Bugs 166 -- 2024-03-11
Bugs in LLM Training – Gradient Accumulation Fix 81 -- 2024-10-16
Long-Context GRPO 60 -- 2025-02-21
Train your own R1 reasoning model 11 -- 2025-02-06
Run Qwen3-Coder-480B-A35B Locally with Unsloth Dynamic Quants 8 -- 2025-07-23
How to Run QwQ-32B effectively 4 -- 2025-03-07
Long context GPT-OSS fine-tuning 4 -- 2025-08-28
Unsloth: GLM-4.7-Flash 4 -- 2026-01-20
2x faster Gemma 2 finetuning and 63% less VRAM 3 -- 2024-07-04
Unsloth: 30x faster AI training 3 -- 2023-12-01
Unsloth: Easily finetune and train LLMs Get faster with unsloth 3 -- 2024-11-07
Dynamic 4bit Quantization 3 -- 2024-12-04
Run DeepSeek-V3-0324 locally 3 -- 2025-03-26
How to Run Deepseek-V3-0324 Locally 3 -- 2025-03-29
Deepseek-R1-0528 Dynamic 1-bit 3 -- 2025-05-29
Qwen3-Coder: How to Run Locally 3 -- 2025-07-25
Unsloth Dynamic 2.0 GGUFs 3 -- 2025-07-27
Unsloth Dynamic GGUFs DeepSeek (671B) outperforms SOTA models 3 -- 2025-09-10
Kimi K2 Thinking: How to Run Locally 3 -- 2025-11-08
1.8-3.3x faster Embedding finetuning now in Unsloth 3 -- 2026-01-22
CodeLlama-34B 13x faster finetuning 2 -- 2023-12-16
Finetune and Run Llama 4 with Unsloth 2 -- 2025-04-06
Unsloth Dynamic v.20 GGUFs 2 -- 2025-04-30
Run and Fine-Tune Qwen3 2 -- 2025-04-30
Kimi K2: How to Run Locally 2 -- 2025-07-15
Show HN: GPT OSS: How to run and fine-tune 2 -- 2025-08-08
Fine-Tuning LLMs with Nvidia DGX Spark and Unsloth 2 -- 2025-10-17
How to Run Qwen-Image-2512 Locally in ComfyUI 2 -- 2025-12-31
Continued LLM Pretraining with Unsloth 1 -- 2024-06-05
Unsloth: GPT-OSS 1 -- 2025-08-05
How to Run Local LLMs with Claude Code and OpenAI Codex 1 -- 2026-01-29
Plushcap, by Matt Makai. 2021-2026.