Hacker News new | ask | show | jobs
user: anuarsh
created: 2025-08-28
karma: 53

submissions:

Show HN: Fine-tune Llama3-8B on 8GB GPU without quantization
3 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput
123 points | 17 comments
Show HN: Run gpt-oss-20b on 8GB GPUs
6 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Show HN: oLLM – LLM Inference for large-context tasks on consumer GPUs
3 points | 7 comments