Newshot Original text(via HN AI)
| Ask HN: Which open source LLM works best locally, and on what hardware? | ||
|---|---|---|
| 3 points by donkan168 17 minutes ago │ hide │ past │ favorite │ 5 comments |
| jpsanders 3 minutes ago │ next [–] if you have a GTX 1060 6GB this might help you: " https://github.com/jpsanders/pascal-llm-stack " reply | jpsanders 3 minutes ago │ next [–] if you have a GTX 1060 6GB this might help you: " https://github.com/jpsanders/pascal-llm-stack " reply | ||
|---|---|---|---|
| jpsanders 3 minutes ago │ next [–] if you have a GTX 1060 6GB this might help you: " https://github.com/jpsanders/pascal-llm-stack " reply | |||
| tourmalinetaco 7 minutes ago │ prev │ next [–] You can try: https://runitlocal.io/ Saw it on here a few days ago, you put in your GPUs and it helps give you an idea of what you can run. Although, the specific model weight is dramatically altered by use case. Do you want code creation? Creative writing? Assistant workloads? I would suggest doing some Googles/AI searches on “[Model returned by RunItLocal] for [use case]”. reply | tourmalinetaco 7 minutes ago │ prev │ next [–] You can try: https://runitlocal.io/ Saw it on here a few days ago, you put in your GPUs and it helps give you an idea of what you can run. Although, the specific model weight is dramatically altered by use case. Do you want code creation? Creative writing? Assistant workloads? I would suggest doing some Googles/AI searches on “[Model returned by RunItLocal] for [use case]”. reply | ||
| tourmalinetaco 7 minutes ago │ prev │ next [–] You can try: https://runitlocal.io/ Saw it on here a few days ago, you put in your GPUs and it helps give you an idea of what you can run. Although, the specific model weight is dramatically altered by use case. Do you want code creation? Creative writing? Assistant workloads? I would suggest doing some Googles/AI searches on “[Model returned by RunItLocal] for [use case]”. reply | |||
| donkan168 4 minutes ago │ parent │ next [–] oh thank you, I'll review it, good resource thank you again reply | donkan168 4 minutes ago │ parent │ next [–] oh thank you, I'll review it, good resource thank you again reply | ||
| donkan168 4 minutes ago │ parent │ next [–] oh thank you, I'll review it, good resource thank you again reply | |||
| spottedmarley 15 minutes ago │ prev [–] best for what? reply | spottedmarley 15 minutes ago │ prev [–] best for what? reply | ||
| spottedmarley 15 minutes ago │ prev [–] best for what? reply | |||
| donkan168 10 minutes ago │ parent [–] fair enough, I mostly meant for reasoning and coding, but feel free to share whatever you use and its strengths reply | donkan168 10 minutes ago │ parent [–] fair enough, I mostly meant for reasoning and coding, but feel free to share whatever you use and its strengths reply | ||
| donkan168 10 minutes ago │ parent [–] fair enough, I mostly meant for reasoning and coding, but feel free to share whatever you use and its strengths reply |
Saw it on here a few days ago, you put in your GPUs and it helps give you an idea of what you can run. Although, the specific model weight is dramatically altered by use case. Do you want code creation? Creative writing? Assistant workloads? I would suggest doing some Googles/AI searches on “[Model returned by RunItLocal] for [use case]”.