Search: unsloth.ai | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning (github.com/unslothai)

385 points

3 years ago

2.

I optimised my vibe coding tech stack cost to $0

12 points

5 months ago

3.

Show HN: Run Unsloth Dynamic GGUFs using Docker model runner (github.com/docker)

3 points

7 months ago

4.

Run DeepSeek R1 Dynamic 1.58-bit (unsloth.ai)

767 points

a year ago

5.

How to run Qwen 3.5 locally (unsloth.ai)

490 points

3 months ago

6.

Qwen3.5 Fine-Tuning Guide (unsloth.ai)

416 points

3 months ago

7.

Unsloth Studio (unsloth.ai)

388 points

3 months ago

8.

Unsloth Dynamic 2.0 GGUFs (unsloth.ai)

237 points

3 months ago

9.

Fine-tune Google's Gemma 3 (unsloth.ai)

226 points

a year ago

10.

Phi-4 Bug Fixes (unsloth.ai)

193 points

a year ago

11.

GPT-OSS Reinforcement Learning (docs.unsloth.ai)

180 points

8 months ago

12.

Fixing Gemma Bugs (unsloth.ai)

166 points

2 years ago

13.

Making LLM Training Faster with Unsloth and NVIDIA (unsloth.ai)

129 points

a month ago

14.

Bugs in LLM Training – Gradient Accumulation Fix (unsloth.ai)

81 points

2 years ago

15.

Long-Context GRPO (unsloth.ai)

60 points

a year ago

16.

Run DeepSeek R1 Dynamic 1.58-bit (unsloth.ai)

19 points

a year ago

17.

Train your own R1 reasoning model (unsloth.ai)

11 points

a year ago

18.

Unsloth Joins PyTorch Ecosystem (unsloth.ai)

8 points

24 days ago

19.

Run Qwen3-Coder-480B-A35B Locally with Unsloth Dynamic Quants (docs.unsloth.ai)

8 points

10 months ago

20.

Train your own R1 reasoning model with Unsloth (unsloth.ai)

6 points

a year ago

21.

Qwen3.5 GGUF Benchmarks (unsloth.ai)

5 points

3 months ago

22.

How to Run QwQ-32B effectively (docs.unsloth.ai)

4 points

a year ago

23.

Unsloth creators fix universal error with gradient accumulation (unsloth.ai)

4 points

2 years ago

24.

Claude Code makes local LLMs 90% slower (unsloth.ai)

4 points

3 months ago

25.

Long context GPT-OSS fine-tuning (unsloth.ai)

4 points

9 months ago

26.

Qwen3-Coder-Next: How to Run Locally (unsloth.ai)

4 points

4 months ago

27.

Unsloth: GLM-4.7-Flash (unsloth.ai)

4 points

4 months ago

28.

Dynamic 4bit Quantization (unsloth.ai)

3 points

a year ago

29.

1.8-3.3x faster Embedding finetuning now in Unsloth (unsloth.ai)

3 points

4 months ago

30.

2x faster Gemma 2 finetuning and 63% less VRAM (unsloth.ai)

3 points

2 years ago