HN
Hacker News
Top
New
Best
Ask
Show
Jobs
anuarsh
53 karma · joined August 28, 2025
submissions
comments
Show HN: Fine-tune Llama3-8B on 8GB GPU without quantization
github.com
·
3 pts
·
anuarsh
·
0
Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput
github.com
·
123 pts
·
anuarsh
·
17
Show HN: Run gpt-oss-20b on 8GB GPUs
github.com
·
6 pts
·
anuarsh
·
0
Show HN: oLLM – LLM Inference for large-context tasks on consumer GPUs
github.com
·
3 pts
·
anuarsh
·
7