Topics

Explore topics

#ollama

Follow to get notified about new posts with this tag
popularai
local
22d
How much VRAM do you really need for a local LLM?
How much VRAM do you really need for a local LLM?
How much VRAM does a local LLM really need? A model can fit comfortably on your GPU, then suddenly spill onto the CPU after one setting changes. Here's why the usual VRAM charts can mislead you. Read the
0
popularai
local
1M
How to make local AI answer questions about your PDFs without inventing sources
How to make local AI answer questions about your PDFs without inventing sources
Want to chat with your PDFs without uploading them to the cloud? This local RAG setup uses Ollama to answer from your files with citations you can actually check. Read the full article on Popular AI
0
1
popularai
local
1M
How to build a private Alexa alternative with Home Assistant and a local LLM
How to build a private Alexa alternative with Home Assistant and a local LLM
Can you replace Alexa with a local AI assistant? Home Assistant + Ollama gets surprisingly close, with one big tradeoff most setups gloss over. Read the full article on Popular AI
popularai
ollama
3M
Ollama sees your AMD GPU but uses CPU? Fix ROCm 7 first
Ollama sees your AMD GPU but uses CPU? Fix ROCm 7 first
Your AMD GPU can be detected perfectly and Ollama can still dump the whole model onto your CPU. Before blaming the Radeon card, check the software mismatch that can make good hardware look broken. Read
popularai
ollama
3M
OLLAMA_NUM_PARALLEL not working on Mac MLX? Here is why
OLLAMA_NUM_PARALLEL not working on Mac MLX? Here is why
Set OLLAMA_NUM_PARALLEL to 4 or 8 on your Mac and still watching Ollama queue requests one by one? The setting may be fine. The real bottleneck is hiding somewhere else. Read the full article on Popular
burntokens
news
4M
Benchmarking Qwen 3.5 0.8B for Automated Title Generation
Benchmarking Qwen 3.5 0.8B for Automated Title Generation
When building local automation pipelines, choosing the right Small Language Model (SLM) and tuning its parameters is essential to getting consistent, constrained outputs. In this test, I evaluated Qwen
burntokens
vyb
4M
Finding the Best CPU-Only LLM for Short Title Generation: Qwen 3.5 (0.8b 4b 9b) Benchmarks
Finding the Best CPU-Only LLM for Short Title Generation: Qwen 3.5 (0.8b 4b 9b) Benchmarks
Can you reliably run Small Language Models (SLMs) locally on a standard CPU without a dedicated graphics card? If you're looking for an efficient local model to handle specific tasks like post title
rubenstorm
ai
4M
Rate Limits in AI: A Personal Journey from Data Loss to a Local Solution
Rate Limits in AI: A Personal Journey from Data Loss to a Local Solution
AI throttling, data loss, and a local Ollama solution for privacy‑focused digital nomads.
ackza
Proof of Brain
1y
Hive users NEED a cheap Ai Mini PC and to PRACTICE with your own PRIVATE LLM! Downloading OLLAMA Open Source Ai $200 to $2000 Ai Mini PC like a $300 jetson one or mac Mini- also I want a collaboratively editable hive front end.
Hive users NEED a cheap Ai Mini PC and to PRACTICE with your own PRIVATE LLM! Downloading OLLAMA Open Source Ai $200 to $2000 Ai Mini PC like a $300 jetson one or mac Mini- also I want a collaboratively editable hive front end.
Iv'e talked about how Hive users need 3d printers, and Meshtastic digital radio pagers for some sort of decentralized local piratebox hive posting, and now I think Hive users all need to start buying these
darthgexe
Programming & Dev
2y
Local integration of DeepSeek-r1 in VSCode [Eng/Esp]
Local integration of DeepSeek-r1 in VSCode [Eng/Esp]
A guide to Install DeepSeek-R1 locally with Ollama and integrating it into VS Code
oflyhigh
HIVE CN 中文社区
2y
我的家庭AI助手成功上线
我的家庭AI助手成功上线
继续研究火爆全网的DeepSeek，话说我将使用这个大模型（问答）归纳为几种方法：网络版、本机版以及本地网络版。 (插图由ChatGPT生成） 网络版的好处是随时随地可以，而且部署的是最新最强大的版本，不足之处嘛，据说由于DDoS攻击，现在访问还可以卡。（还有就是API应该是收费的） 本机版好处就是在本机上随时可用，缺点嘛，对电脑配置要求极高，而且没法部署满血的大模型，我在我的11代Intel NUC
oflyhigh
HIVE CN 中文社区
2y
三分钟在本地运行DeepSeek R1推理模型
三分钟在本地运行DeepSeek R1推理模型
最近一段时间DeepSeek R1可谓是大出风头，火爆全网，据说表现可以和OPEN AI等顶级模型相媲美，训练成本又比其它大模型低廉得很，导致英伟达股票都大跌了呢。 (图源 ：pixabay) 话说O哥不是AI领域的专家，这些大模型孰优孰劣完全是一头雾水，基本是就是拿来生成个图片呀，翻译一段英文呀，或者写一段示例代码之类的。
rivalhw
HIVE CN 中文社区
2y
人人都能用的起的免费大模型：尝试本地安装和使用Ollama大模型（llama3.3 ，llama3.2）
人人都能用的起的免费大模型：尝试本地安装和使用Ollama大模型（llama3.3 ，llama3.2）
周六收到邮件，看到AI大模型Ollama开源了新版本 Llama 3.3 ，不仅有70B，还支持中文版，不禁心里有些痒痒，打算尝试下载使用下。 我之前安装过Llama 3.2，不过是1B而已，而且貌似当时不支持中文，你让它用中文回答，它却用拼音糊弄你。。。实在尴尬的很，囧囧囧。。。 老样子，上github上，下载大模型先。
mhecrypto518
ai
2y
!Low reputation account with an unverified outbound link, Reveal content
Unlock Your Future with Omni AI: Win 1000 Credits!
Unlock Your Future with Omni AI: Win 1000 Credits!
Omni AI is your gateway to revolutionary AI technology, and we’re giving you a chance to win 1000 free credits!
mhecrypto518
ai
2y
!Low reputation account with an unverified outbound link, Reveal content
"Unlock Your Potential: How AI Can Transform Your Everyday Life"
"Unlock Your Potential: How AI Can Transform Your Everyday Life"
Discover how AI can revolutionize your projects and simplify your life! Whether you're new to AI or an innovator seeking the latest tools.
achimmertens
Learn to Code
2y
Running Ollama locally and training the AI - Ollama lokal laufen lassen und die KI trainieren
Running Ollama locally and training the AI - Ollama lokal laufen lassen und die KI trainieren
How to run and train ai models locally with ollama. - Wie man KI Modelle lokal trainiert und laufen lässt.
ackza
DBuzz
3y
#ollama is a PRIVATE #ai #llm #largelanguagemodel you can run on your own device, at home or in a network of blockchain connected servers (LIKE HIVE IN THE FUTURE!) Imagine private Ais producing powerful

Discover communities

Explore communities
Create your community