Skip to content
TheChatArchiveThe Chat Archive
o4-mini-2025-04-16· OpenAIHugging Face LMArena Human Preference 140K

whats the best llm for an average person to replace something like chatgpt for daily…

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Mistralmistral-medium-2505’s answer.
  1. User

    whats the best llm for an average person to replace something like chatgpt for daily tasks and life/universe questions

  2. Assistant

    Here are a few strong contenders you can use “in place of” ChatGPT—whether you want something you can run completely locally, tap via API, or just out-of-the-box free. I’ve ordered them roughly by how “average-user friendly” they are:

    ModelSourceHow to AccessStrengthsCaveats
    OpenAI GPT-3.5-TurboOpenAI (API)Sign up for free API creditsVery capable generalist; low costRequires internet & API key
    Llama 2 Chat (7B/13B)Meta (open source)Hugging Face, Docker imagesLocal run; good “chat” fine-tuningNeeds decent GPU (8–12 GB VRAM)
    Mistral Instruct MixMistral AI (open)Hugging Face, ReplicateExcellent “instruction following”~10 GB VRAM; a bit newer/unproven
    Anthropic Claude 2Anthropic (API)Invite/API keyVery safe/filtered; strong long-formStill “in closed beta” pricing
    Vicuna (7B)Community fine-tuneLocal via Hugging FaceSuperb chat quality for 7B footprintLarge prompt overhead; tricky install

    —

    Quick Recommendations

    1. If you just want “ChatGPT-like” and don’t mind API calls:
      • GPT-3.5-Turbo. Free tier is generous; rock-solid generalist.
    2. If you’d like total offline privacy (and have a capable PC):
      • Llama 2 Chat 7B or 13B. Easy to spin up via Docker or a simple Python script.
    3. If you love bleeding-edge open-source:
      • Mistral Instruct Mix (if you can carve out the VRAM). It often edges out Llama 2 on instruction tasks.

    —

    What to consider

    • Cost: API hits vs. free local inference
    • Hardware: Do you have a GPU with ≥8 GB VRAM? If not, cloud/API is easier.
    • Privacy: Local models never phone home; APIs do.
    • Ease of use: OpenAI & Anthropic give you polished playgrounds. Open-source may need a bit of tinkering.

    Feel free to ask more about setup, pricing comparisons, or how to host these on your own machine! 😊

  3. User

    i have 96gb of ram and a 5090

  4. Assistant

    With your beefy 96 GB RAM + an RTX 5090, you can comfortably run large local models—up to ~70 B parameters (in 4-bit quant) or mid-sized ones in full precision. Below is a quick breakdown of top picks for “ChatGPT-style” daily chats, and roughly what you’ll need:

    ModelApprox. VRAM (fp16)Quantized VRAM (4-bit)StrengthsNotes
    Mistral 7B~14 GB~7 GBSOTA small model—sharp instruction following, very snappyGreat “first install” in text-generation-webui
    Llama 2 Chat 13B~20 GB~10 GBOfficial “chat” finetune by Meta; solid generalistPlug-and-play with Hugging Face recipes
    Falcon 40B~48 GB~24 GBUltra-capable on reasoning + code tasksYou’ll need the 4-bit GPTQ quant; 40B is heavy
    Llama 2 Chat 70B~85 GB~35 GBVery close to GPT-3.5-level quality4-bit quant required + some CPU offload
    MPT-30B Instruct~40 GB~20 GBExcellent for “instruct” style promptsOpen-source; has code & Q/A strengths

    —

    Top 2 Recommendations

    1. Mistral 7B (4-bit)
      • VRAM: ~7 GB (super light)
      • Speed: ~200 tokens/sec on your 5090
      • Why: Best “bang for buck” open-source chat model. Minimal fuss to get going—just grab the HF weights + text-generation-webui.
    2. Llama 2 Chat 13B (4-bit)
      • VRAM: ~10 GB
      • Speed: ~120 tokens/sec
      • Why: Officially supported “chat” finetune, very reliable on multi-turn convo and safe outputs.

    —

    If you want to push quality to the max

    • Falcon 40B or Llama 2 70B in 4-bit: You’ve got the headroom. Expect ~24–35 GB VRAM usage, blazing results on deep Q&A, coding, brainstorming.

    —

    Getting Started

    1. Install text-generation-webui (or Hugging Face LLM runner).
    2. Download your chosen weights (e.g. mistral-7b-instruct).
    3. Launch in 4-bit mode with bitsandbytes:
      python server.py \
        --model mistral-7b-instruct \
        --load-in-4bit \
        --bnb-config bitsandbytes-config.json
      
    4. Fire up the local playground at http://localhost:7860 🎉

    Feel free to ask for a step-by-step setup guide, prompt-engineering tips, or how to squeeze even more performance out of your rig!

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.