Latest activity Postings About Feedback Stats
-
-
Party Monger replied to the thread What's your perspective on the India's future?.To answer the question in the Title, this is the perspective on India's future - -
Party Monger replied to the thread Perplexity Pro - 499₹ [ 1 Year Promo Code ✅ ].Chatgpt provides more resources, so more processing goes into answers, and they're more creative sometimes. But this is absolute value...
-
Party Monger replied to the thread English TV series discussion.Wheel of Time current season is decent. Current and last season were significantly better than the first season. The more we get into...
-
Party Monger replied to the thread Monitors OLED Monitors.As someone using C3 48in as monitor I agree. I love it with the new mount. Best to get these. Can easily be repurposed too later.
-
Party Monger replied to the thread PC Peripherals Need printer recommendation (B/W only).Printer - Brother HL2321d. When it finishes, get a formujet toner from amazon and refills. Keep refilling on your own. Using since 2019...
-
Party Monger replied to the thread Storage Solutions How good are silicon power, evm, orico, etc ssd ?.For anything serious stick to wd, Samsung, seagate etc.
-
Party Monger replied to the thread How to run large LLMs like Llama 3.1 70B or Mixtral 8x22B with limited GPU VRAM?.Thanks bro will try this.
-
Party Monger reacted to thetechguy's post in the thread How to run large LLMs like Llama 3.1 70B or Mixtral 8x22B with limited GPU VRAM? with
Like.
@Party Monger ollama is the simplest. ollama pull mistral For ui, docker run -p 8080:8080 open-webui/open-webui -
Party Monger reacted to ishashank's post in the thread How to run large LLMs like Llama 3.1 70B or Mixtral 8x22B with limited GPU VRAM? with Like.
Use Jan ai, one of the best and open source.
-
Party Monger reacted to sporkydork's post in the thread How to run large LLMs like Llama 3.1 70B or Mixtral 8x22B with limited GPU VRAM? with Like.
How about lmstudio? I tried it out on a windows 10 machine with 16gb ram and ran the lowest model of deepseek AI for a test. Worked out...
-
Party Monger replied to the thread How to run large LLMs like Llama 3.1 70B or Mixtral 8x22B with limited GPU VRAM?.I tried it before. Is there anythhing better with good interface
-
Party Monger replied to the thread How to run large LLMs like Llama 3.1 70B or Mixtral 8x22B with limited GPU VRAM?.What's the best way to run LLMs on Mac? Have 64gb ram M2 max
-
Party Monger reacted to Kunal_Rai's post in the thread Perplexity Pro - 499₹ [ 1 Year Promo Code ✅ ] with Like.
Thanks for purchasing. Yes! Pro users get at least 300 Pro Searches per day. I think he meant how many devices he can log into his...
-
Party Monger reacted to ibose's post in the thread Perplexity Pro - 499₹ [ 1 Year Promo Code ✅ ] with Like.
Q14 on this page suggests unlimited devices - https://www.singtel.com/personal/my-account/rewards-perplexity-prestige/faqs Best to ask...
-
Party Monger reacted to kuduku's post in the thread Perplexity Pro - 499₹ [ 1 Year Promo Code ✅ ] with Like.
I was using it on 6 simultaneous logins from past 8/9 months
-
-
Loading…
-
Loading…
-
Loading…