Gavin Li
@lyogavin
Anima AI Founder,CEO
3
Published Tools
0
Total Stars
0
Weekly Downloads
1,210
GitHub Followers
68
Public Repos
Published Tools
3 Skillsacross 2 categoriesGavin Li
AirLLM runs 70B large language models on a single 4GB GPU without quantization, distillation or pruning. 405B Llama 3.1 on 8GB, DeepSeek-V3 671B on ~12GB.
...moreSkilluncategorised
1 dir
Gavin Li
BetterAirLLM allows single 4GB GPU card to run 70B large language models without quantization, distillation or pruning. 8GB vmem to run 405B Llama3.1.
...moreSkillai-ml
1 dir
Gavin Li
PetaLLM allows single 4GB GPU card to run 70B large language models without quantization, distillation or pruning. 8GB vmem to run 405B Llama3.1.
...moreSkillai-ml
1 dir