Model selection and compatibility
Support for and practical use of Qwen, Gemma, Hermes, Llama, DeepSeek, and other open-weight models in LM Studio.
51.7%
Best tweets about LM Studio
29 Best Tweets About LM Studio (2026)
Browse the best tweets about LM Studio, featuring local LLM setup, model downloads, hardware performance, local servers, APIs, and private AI workflows.
Specific LM Studio setup, local inference, model compatibility, hardware performance, APIs, troubleshooting, and releases.
- Creators
- 27
- Updated
Original Xholic analysis
What 29 top LM Studio posts reveal
LM Studio discussion centers on private local setup, hardware-matched model selection, and connecting local models to APIs and agent workflows. The largest engagement outliers were ownership- and setup-oriented guides, while hands-on posts also document speed, memory, vision, and model-quality constraints.
- Dominant tone
- Positive
- Median score
- 17.2
- Leading format
- Other
- Recent posts
- 34.5%
69% of posts
All-time engagement
100% of posts
Published in 90 days
Conversation map
The themes creators return to
APIs, agents, and app integrations
Using LM Studio's local OpenAI-compatible server or custom endpoints with agents, coding tools, desktop apps, and API clients.
48.3%
Local setup and private inference
Installing LM Studio, downloading a suitable local model, and using it as a private offline ChatGPT-style assistant.
48.3%
Hardware compatibility and performance
Matching model parameter size and quantization to RAM/VRAM, with benchmarks and trade-offs in tokens per second, context, memory bandwidth, and quality.
37.9%
Local AI ownership and autonomy
Privacy, cost savings, offline availability, and independence from cloud providers as motivations for running models locally.
20.7%
Releases and local AI ecosystem
LM Studio feature announcements and ecosystem developments, including Hermes integration, MLX support, llama.cpp foundations, and newly released multimodal models.
20.7%
Remote inference and networking
LM Link, Tailscale, and remote-inference setups that let lightweight devices access models running on a more powerful local machine.
13.8%
Troubleshooting and limitations
Troubleshooting LM Studio model behavior, including broken vision support, constrained laptop performance, and configuration questions around skills and MCPs.
13.8%
Tone and stance
Sentiment Positive leads
Author posture Supportive leads
Performance benchmark
- Median likes
- 38
- Median reposts
- 4
- Median replies
- 5
- Median views
- 4.3K
Posts with media make up 69% of this collection. Their median all-time score is 14.0, compared with 28.4 for text-only posts.
Format mix
- Other 100% Β· score 17.2
Consensus and debate
Where creators agree, and where they do not
Shared view
Local setup follows a hardware-aware sequence
Recurring setup guides recommend choosing LM Studio (or another runtime), selecting a model and quantization that fit the machine, and configuring a local API for an agent or workflow.
Shared view
Local serving connects models to other tools
Posts show LM Studio serving locally to other tools: OpenClaw is configured to use its API, Raycast is pointed at localhost:1234/v1, and AnythingLLM is used with LM Studio as a server.
Shared view
Model selection and runtime compatibility remain central
Model discussion includes Qwen, Gemma, DeepSeek, Llama, and other open-weight options. Gemma 4 posts list LM Studio among the available runtimes, while a Qwen post highlights use with LM Studio.
Open debate
The autonomy argument meets value skepticism
Ownership-oriented guides cite privacy, savings, and local control. A cautionary post argues that a roughly US$4,000 local box may still deliver results inferior to inexpensive commercial offerings in current practice.
Open debate
Hardware matching helps, but performance remains constrained
Guides present quantization and hardware matching as ways to make local models usable, while hands-on posts report that 120B+ models can be slow without strong GPUs and that speed varies by device and task. One ThinkPad test reported about 5 tok/s on simple prompts and 1.4 tok/s on a harder reasoning prompt.
What performs
Patterns behind standout posts
Setup and ownership guides produced the largest outliers
The three largest engagement outliers were setup-oriented posts. Together, they cover local-model ownership, hardware-aware model selection, and connecting local models to agent APIs.
Remote inference outperformed its volume
Remote inference accounts for 13.8% of tweets but has a 29.4 median all-time score. The examples use LM Link and Tailscale to access models on a stronger local machine from another device.
Troubleshooting drew concentrated attention
Troubleshooting and limitations has the highest theme median all-time score, at 32.39. Reported issues include vision problems with Gemma 4 12B in LM Studio, a 31B Gemma variant that was broken on one laptop, and questions about custom skills, integrations, and MCPs.
Statistical standouts
- View standout post 1 Score 1847.4 Β· 107.28Γ median
- View standout post 2 Score 1802.4 Β· 104.67Γ median
- View standout post 3 Score 744.1 Β· 43.21Γ median
- View standout post 4 Score 118.3 Β· 6.87Γ median
- View standout post 5 Score 95.7 Β· 5.56Γ median
Creator landscape
Who shapes this conversation
The five most represented creators account for 24.1% of the selected posts.
-
1. AshutoshShrivastava
@ai_for_success
2 posts
-
2. Alex Finn
@AlexFinn
2 posts
-
3. Vaishnavi
@_vmlops
1 post
-
4. Louis Gleeson
@aigleeson
1 post
-
5. andrew chen
@andrewchen
1 post
-
6. Francesco Di Donato
@did0f
1 post
Alex Finn focuses on local ownership and practical scope
Alex Finnβs two posts present LM Studio as an accessible route to private local models and agent-connected APIs. The latter also notes that smaller hardware may be better suited to replacing smaller workflows rather than every AI call.
Gemma coverage combines release information with testing
AshutoshShrivastavaβs posts pair a Gemma 4 release overview with a hands-on LM Studio result: Gemma 4 12B text ran at 28T/s in one test, while vision had issues.
How this analysis was made
Themes, sentiment, stance, and post format are classified per tweet. All counts, shares, medians, creator concentration, freshness, and performance comparisons are then calculated directly from the published snapshot.
Xholic's all-time score compares engagement while accounting for reach, post age, and creator consistency. It is used for relative comparisons within this collection.
This report analyzes the exact 29-post snapshot shown below. AI identifies editorial categories and drafts explanations; all statistics are calculated from the snapshot, and every narrative claim is checked against cited posts before publication.
Best LM Studio tweets
Top LM Studio tweets from 27 creators
Ranked 01β29
- 01
@AlexFinn Β·
I don't care what computer you have, you should be running local models It will save you a money on OpenClaw and keep your data private Even if you're on the cheapest Mac Mini you can be doing this Here's a complete guide: 1. Download LMStudio 2. Go to your OpenClaw and say what kind of hardware you have (computer and memory and storage) 3. Ask what's the biggest local model you can run on there 4. Ask 'based on what you know about me, what workflows could this open model replace?' 5. Have OpenClaw walk you through downloading the model in LM Studio and setting up the API 6. Ask OpenClaw to start using the new API Boom you're good to go. You just saved money by using local models, have an AI model that is COMPLETELY private and secure on your own device, did something advanced that 99% of people have never done, and have entered the future. There are some amazing local models out there too right now. Nemotron 3 and Qwen 3.5 are fantastic and can be ran on smaller devices Own your intelligence.
- 02
@gregisenberg Β·
The takeaway from Fable 5 being BANNED by the government: GET GOOD AT LOCAL MODELS SO YOU HAVE 100% CONTROL. My entire weekend was going to be building my craziest ideas with Fable 5. That's now cancelled. So instead of building with Fable this weekend, I've decided I'll go deep on local models: 1. Start with the runtime. Download Ollama or LM Studio first. This is the thing that actually runs models on your machine. 2. Match the model to your hardware. A model's size is measured in billions of parameters (7B, 32B, 70B). Bigger is smarter but needs more memory. Rule of thumb: a 7B model runs on almost any laptop, a 32B needs a good Mac with 32GB+ RAM, a 70B needs serious hardware like a DGX Spark or a maxed-out Mac Studio. 3. Know which model for which job. Qwen 3 is the best all-around choice for most tasks. DeepSeek for reasoning and coding. Gemma 4 when you need something tiny that runs on a phone. Llama when you want the biggest community and the most fine-tunes. 4. Quantization. You can shrink a model to run on weaker hardware with barely any quality loss. Look for versions labeled Q4 or Q5. This is how a model that "needs" a server runs on your laptop. Learning this one concept changes everything. 5. Connect it to your agent. Point Hermes or your agent stack at a local model. 6. Context window is your real constraint locally. Cloud models give you huge context for free. Local models make you pay for it in memory. A bigger context window eats RAM fast. Keep your sessions tight and your prompts lean or your machine chokes. 7. Learn to give local models tools. A smaller local model with web search, file access, and code execution beats a giant model with none. The capability gap closes fast when you wire up the right tools. The model is the engine but the tools are the wheels. 8. Fine-tuning is more accessible than you think. You don't need this on day one, but know it exists. You can take an open model and train it on your own data so it gets good at your specific domain. I'll probably do a breakdown at some point on this @startupideaspod if people are into it. The lesson from this ban is basically don't build your entire workflow on something that can disappear with a single letter. Own part of your stack. Local models are insurance. It reminds me when people realized they don't own social media accounts. And then you saw people build email lists etc. I remember running a startup and my biggest traffic source was organic FB. All of a sudden, algo changed, and I lost 99% of my traffic. Same sorta moment (but bigger) for AI. This is a wake up call.
- 03
@AlexFinn Β·
I don't care what kind of hardware you have, you should be running local models Governments are now banning models. Theyβre determining what technology you can and canβt use With local models, you are free and nobody can control you Even if you're on the cheapest Mac Mini you can be doing this Here's a complete guide: 1. Download LMStudio 2. Go to your OpenClaw/Hermes and say what kind of hardware you have (computer and memory and storage) 3. Ask what's the best local model you can run on there (probably will be Gemma 4 or Qwen. if you have a big computer, it will be GLM) 4. Ask 'based on what you know about me, what workflows could this open model replace?' 5. Have OpenClaw walk you through downloading the model in LM Studio and setting up the API 6. Ask OpenClaw to start using the new API Boom you're good to go. You just saved money by using local models, have an AI model that is COMPLETELY private and secure on your own device, did something advanced that 99% of people have never done, and have entered the future. If you are on smaller hardware you probably are not going to replace all your AI calls with this, but you could replace smaller workflows which will still save you good money Own your intelligence.
- 04
@NVIDIARTXSpark Β·
Run the latest @Alibaba_Qwen 3.5 models at blazing speeds on RTX GPUs & DGX Spark using @UnslothAI's GGUF quantizations. π¬ Chat instantly in @LMStudio π€ Drive local coding agentic workflows with Codex & Claude Code (via llama.cpp @ggerganov & @Ollama) βοΈ Fine-tune efficiently via Unsloth Guide π https://t.co/fWtiiz3XyS
- 05
@Forgework_ Β·
Join us in setting up a fully local Hermes Agent using Qwen3.5 on the extremely powerful Framework Desktop! I go over LM studio settings, Tailscale, Hermes Agent setup, and how to sandbox the agent in a raspberry pi. @lmstudio @Alibaba_Qwen @NousResearch @FrameworkPuter
Watch video
- 06
@Sumanth_077 Β·
Train LLMs locally without writing a single line of code! @UnslothAI just released Unsloth Studio - an open-source web UI for training and running models. Here's how it works: You upload a PDF, CSV, or DOCX file. The Data Recipes feature automatically transforms it into a structured training dataset via a graph-node workflow. No manual formatting needed. Then you select a model from Hugging Face or your local files. Pick your training method - LoRA, QLoRA, or full fine-tuning. The UI pre-fills sensible defaults based on your model. Start training and watch live metrics - loss curves, GPU usage, gradient norms. Everything runs locally with 2x faster training and 70% less VRAM than standard setups. Here are the key capabilities: β’ Chat with GGUF and safetensor models - supports tool calling, web search, and code execution in a sandbox. β’ Compare models side-by-side - load your base model and fine-tuned version to see how outputs differ. β’ Export to any format - save your trained models as GGUF, safetensors, or LoRA adapters for use with llama.cpp, vLLM, Ollama, or LM Studio. β’ Multi-modal support - train text, vision, audio, and embedding models all in one interface. It runs 100% offline on your hardware.
Watch video
- 07
@andrewchen Β·
playing around with local AI models after I recently built out my home lab (DGX spark, mac mini, 5090 eGPU, strix halo framework, jet KVM etc). Running both Openclaw and Hermes Agent now. Itβs super fun, def recommend! Lets you geek out, learn about AI, and also buy lots of gadgets lol a few observations: - itβs great for learning about AI. Now I actually care and will try out all the new models as they come out - Qwen 3.6, Gemma 4, etc. When thereβs new tech like TurboQuant and DFlash, you can run them on your machine and see how it changes the performance profile - the software stack is interesting. You can use ollama/LM studio to just dabble, but over time I have things set up with LiteLLM (as a local router for LLM queries, depending on their complexity) going to VLLM. I have a faster model (35B MoE) and then a better model (122B) depending on what Iβm using it for - the βbigβ local models (120B+ parameter) are slow unless you have a souped up GPU card. And not as good as the cloud LLMs. So as you tune your setup for maxing out tokens/s to make it as usable and responsive, you get a much better sense for all the tradeoffs - context window, KV cache, mem usage, mem bandwidth, parameter size, TTFT, etc - for those (like me) coming from SOTA cloud LLMs, you canβt help but compare. The open weight models are all about a year behind, but even then, as a consumer, you are generally running much smaller versions of the best local models. You probably wonβt use anything bigger than a ~120B parameter model (GPT OSS 120B or Qwen 3.6 122B). Local AI models running on consumer hardware have 1/100th the size, are much slower (often 30-50 tok/s versus 100+ to be usable) - but because itβs been ~1year behind, it seems remarkable to think that we might be able to run Opus level local models in 2027. The latest open weight models are already pretty usable (just look at Qwen 3.6 27B dense) but its remarkable that itβll keep improving - the hardware side is interesting. I started out with a Mac Mini, then a Nvidia DGX Spark. I also have a gaming rig. It turns out that the Mac hardware stack (particularly Mac Studios) are really good since they have pretty high bandwidth and large amounts of unified memory so you can run big models. (BUT GOOD LUCK GETTING A MAC STUDIO!). Shortages like crazy, and memory size cuts left and right. GPU cards are very fast, but only run much smaller models (24GB and 32GB are the popular consumer sizes for graphics cards), plus you have to put them in a big PC box. I got a 5090 eGPU but lots of issues with it :(. The new GB10/DGX Spark family of devices have big memory but relatively low memory bandwidth (so not the fastest tok/s) but you get CUDA and the whole ecosystem there - the biggest use case Iβve found with my local AI setup has been simple: lots of summarization and analysis. Iβve dumped all my personal emails and blog posts and google data and created detailed month-by-month markdown files that can then be queries. Every article I bookmark or every YouTube channel I subscribe to is summarized. for me the sweetspot has been low-ish priority, asynch, and where the problem doesnβt require SOTA You could argue that this is a lot of effort and $ for something that could probably be covered by my monthly GPT/Claude subscription. And thatβs true! But the learning is the point :) so whatβs a good way to start? I think you start with whatever you have. Ideally a nice Mac M5 laptop or a gaming PC that already has a good GPU. Just set it up so it stays on, and then point some set of Openclaw jobs at it. Or if you want to invest in a new piece of hardware, the DGX Spark or Strix Halo systems are nice to be able to try out bigger models, or you can go down the rabbit hole setting up racks with GPUs etc. Either way, super fun- highly recommend
- 08
- 09
@ai_for_success Β·
Google DeepMind has released Gemma 4 12B, a unified encoder free multimodal model built for running agentic AI locally on laptops. π₯ - 12B parameter model that runs on laptops with 16GB memory - Encoder free architecture for native image and audio processing - Performance close to the larger 26B MoE model - Native audio support with raw audio token processing - Multi Token Prediction for lower latency - Open sourced under Apache 2.0 - You can try here LM Studio, Ollama, Google AI Edge Gallery App, the Google AI Edge Eloquent app and the LiteRT-LM CLI - New Gemma Skills Repository for agentic workflows
- 10
@FrameworkPuter Β·
One of the coolest uses of @lmstudio and @AIatAMD is using LM Link to have a Framework Desktop be a remote inference server for a laptop, including something little like Framework Laptop 12. It feels native on the laptop, but gets the desktopβs performance.
Watch video
- 11
@hasantoxr Β·
Anthropic Fable 5 has been banned by the government. Learn to use local models so you have 100% control. Instead of arguing about why they banned it, I built a full guide on running AI locally so nobody can ever take it from you. Here's everything you need to know: 1. Pick your runtime first. Think of this like installing a video game launcher before you can play any games. Ollama and LM Studio are the two launchers for AI. Download one. That's step one. 2. Understand model size. The number next to a model like 7B or 32B just means how many things it learned. Bigger number means smarter but needs more memory. A 7B runs on any laptop you already own. Start there. 3. Pick the right model for the job. Qwen 3 for everyday tasks and writing. DeepSeek for math and coding problems. Gemma 3 when your computer is slow. Llama when you want the most help from the internet because millions of people use it. 4. Learn quantization. This sounds scary but it's just shrinking. Like zipping a file. A huge model gets compressed so it fits on your laptop with almost no quality loss. Look for Q4 or Q5 in the model name. That's the compressed version. Download that one. 5. Add tools to your model. A small model with Google search and file access beats a big model with nothing. Think of tools like giving the AI hands. Without them it can only think. With them it can actually do things. 6. Watch your context window. Cloud AI has unlimited memory per conversation. Local AI does not. The longer your chat gets the more your laptop slows down. Keep conversations short. Start a new chat when things feel slow. You never needed anyone's permission to use AI. The ban only hurts people who never learned to run it themselves.
- 12
@heyrimsha Β·
A software engineer in Sofia, Bulgaria wrote 4,000 lines of C++ in March 2023 that made it possible to run Meta's leaked Llama model on a MacBook without a GPU. Within a week every AI engineer on Earth was running his code. 3 years later the project has 115,000 GitHub stars with powers most of the local AI ecosystem and just joined Hugging Face. He had never worked at a major AI lab in his life. His name is Georgi Gerganov and most people just call him ggerganov. Here is the story because almost nobody outside the open-source AI world knows what one engineer in Bulgaria has built. Georgi lives in Sofia. He works from a home office in a country that has no frontier AI lab, no NVIDIA partnership, no Silicon Valley. He had been writing low-level C and C++ for years before LLMs became the center of the universe. He was known in niche corners of the internet for an odd project called kbd-audio, a program that could figure out what someone typed by listening to the acoustic signature of their keyboard. In September 2022 he started working on something called GGML. It was a tensor library written in pure C with no dependencies. The inspiration was Fabrice Bellard's LibNC. The goal was simple. Run machine learning models on regular hardware with no Python, no PyTorch, no CUDA, no cloud. The first real test was whisper.cpp, his port of OpenAI's Whisper speech recognition model. It ran on a laptop. It ran on a phone. It needed nothing but a C compiler. The open-source community started noticing. Then in late February 2023 Meta released Llama, the first serious open-weight large language model. Within a week the weights leaked on 4chan and started spreading across the internet. The catch was that almost nobody could run it. You needed expensive GPUs and a Python environment. The most powerful open model in the world was effectively locked behind hardware most developers did not have. On March 10, 2023, Georgi pushed the first commit to a new repository called llama.cpp. It was an implementation of Llama inference in pure C and C++ with zero dependencies. It ran on CPU. It ran on a MacBook Air. It ran fast. The repository exploded. Within days it had thousands of stars. Within weeks it became the default way to run open-source LLMs on any computer. Quantization support came next, letting you run a 7 billion parameter model in 4GB of RAM. Then a 13 billion parameter model on a phone. Then a 70 billion parameter model on a single high-end consumer card. Today llama.cpp is the inference backbone of the local AI movement. Ollama runs on it. LM Studio runs on it. GPT4All runs on it. Most "run AI on your laptop" tutorials you have ever seen are running Georgi's code underneath. The repository has 115,000 GitHub stars. The community has added Vulkan, OpenCL, Metal, CUDA, and RPC-distributed inference. The K-quant compression methods alone changed how the entire ecosystem thinks about model size. In 2023 Georgi founded ggml AI in Sofia with pre-seed funding from Nat Friedman, the former GitHub CEO, and Daniel Gross. He stayed in Bulgaria. He kept the company small. He kept the code MIT licensed and free forever. In February 2026 Georgi and his core team, including Xuan-Son Nguyen and Aleksander Grygier, joined Hugging Face full-time. The deal was framed as a partnership to scale local AI as a serious alternative to cloud inference. The code stays open. Georgi still answers GitHub issues personally. He still posts releases without press releases. His personal website is a flat page. He still plays semi-professional basketball for a club in his hometown in Bulgaria on the side. A guy in Sofia who had never worked at OpenAI, Google, or Meta wrote the code that runs most local AI on the planet. He did it in a few weeks.
- 13
@ai_for_success Β·
Running Gemma 4 12B locally at 28T/s. Facing issues with vision in LM Studio, but text performance is quite solid. Asked it to create a landing page for a tech event. Video is fast forwarded for the demo.
Watch video
- 14
- 15
@sharbel Β·
Anthropic's API can run $1000+/month at heavy Claude Code usage. Someone built Free Claude Code: A proxy that lets Claude Code talk to free or local model providers instead. It's called free-claude-code. 7,300+ stars on GitHub. Set two environment variables (ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN), point Claude Code at the proxy, done. The CLI and VSCode extension keep working, but behind the scenes you're hitting a different model, not Claude. What it supports: β Routes to NVIDIA NIM's free tier (rate-limited). β OpenRouter, including free model tiers. β DeepSeek direct API. β LM Studio / llama.cpp for fully local inference. β Per-model routing: different provider per Claude model tier. β Thinking-token parsing into Claude thinking blocks. β Heuristic tool-call parser for models without native tool use. β Discord / Telegram bot for remote coding sessions. Real trade-offs to know: - Quality drops. Backing models are not Claude. Tool use is less reliable (that's why the heuristic parser exists). Agentic tasks that Sonnet or Opus nail will fail more often on free tiers. - Free tiers aren't permanent. NIM / OpenRouter / DeepSeek quotas and pricing can change. - Data path changes. Your prompts and code now flow through whichever provider you route to, with their retention policy, not Anthropic's. Worth it for tinkering, offline work, or non-sensitive side projects. Not a drop-in replacement for paid Claude on client code or serious engineering. If your actual goal is "pay less for Claude Code at full quality," the Claude Pro sub ($20/mo) or Max tier ($100-200/mo) includes Claude Code usage directly, no API key needed. MIT licensed. 100% open source.
- 16
@aigleeson Β·
Claude Code just got a free mode. Not official. A developer built a repo that routes Claude Code calls to free and local AI models. Instead of buying Anthropic credits... You can run it with: > NVIDIA NIM > OpenRouter free models > DeepSeek > LM Studio > llama.cpp Best part: Claude Code does not need to change. You just point it at a local proxy and it works. This turns Claude Code from βpaid coding agentβ into βbring your own model agent.β Huge for indie devs. https://t.co/ua4nHZG28m
- 17
- 18
@_vmlops Β·
GEMMA 4 12B JUST CHANGED LOCAL AI DEVELOPMENT google dropped an encoder-free multimodal model no separate vision encoder. no audio encoder. just one decoder-only transformer handling everything β«οΈ raw pixel patches projected directly to LLM hidden dim β«οΈ raw 16kHz audio sliced into 40ms frames, fed straight in β«οΈ LoRA/full fine-tuning updates all modalities in a single pass β«οΈ runs locally on 16GB VRAM β«οΈ OpenAI-compatible local API server via `litert-lm serve` the wild part...? it can process 5 minutes of video at 1FPS with audio, and build a working Gradio app using itself as the backend one model. vision + audio + text. zero encoder overhead. available on Hugging Face, Ollama, LM Studio & vLLM today
Watch video
- 19
- 20
@lemire Β·
AMD is coming up with its small AI PC (AI Halo). It will compete against NVIDIA DGX Spark. Both look a bit like a mac Mini. Just a tiny box. The AI Halo should cost US$4000, so it is accessible to hobbyists and small IT departement. Set it up with LM Studio with its llama.cpp backend and you got yourself a 'ChatGPT-like' experience from your own network. Both the AI Halo and the Spark have 128GB of 'unified' RAM (meaning that the memory is shared between CPU and GPU). It is the same type of memory you get on your macBook (LPDDR5X), so it is not the fancy high-bandwidth memory you get on GPU cards... but it is good enough. So I played with llama.cpp and I was running open source models last year. It is pretty cool getting this silly little C++ program (llama.cpp) that answers you back when you ask questions... right there on your machine. But I think that most people will be somewhat disappointed in practice. It is close to Big AI models, but still obviously inferior to even the cheap commercial offerings. If you have US$4000 to burn, you are better off spending it on tokens from an AI provider. That's short term. Long term... Who knows? Linux started out as a toy. It is now running the Internet. Give it 5, 10, 20 years and maybe these little boxes could be everywhere.
- 21
@JulianGoldieSEO Β·
Want to run Hermes for free forever? Here is the simple setup: 1. Download LM Studio 2. Search the Hermes focused local model 3. Download the quant that fits your machine 4. Start the model locally 5. In Hermes, switch your model to localhost or custom endpoint That is it. You get a local Qwen 3.5 based model tuned for agent workflows, without needing a paid API. For Hermes users, this is one of the most interesting local model drops in a while.
Watch video
- 22
@SaiyamPathak Β·
Yesterday in the video I took - the qwen32B which was a dense 32B and all active parameters for every token whereas for the MLX version it was A3B - active 3B. this morning I ran some tests again: - Qwen3.5 (NVFP4, MLX): 23.11 tok/s decode - Nemotron (GGUF, llama.cpp): 21.70 tok/s decode So not that much of a difference - maybe llamacpp already good for M1 type - I need to test it across all architectures though. Interestingly I tested the LMstudio as well that had the MLX support for quite some time now. results are pretty interesting and I tried kind of similar models although its not apples to apples. LM Studio - MLX - Qwen3.5-35B-A3B-4bit - 33.82 tok/s Ollama - MLX - qwen3.5:35b-a3b-coding-nvfp4 - 23.11 tok/s the 4-bit quantization is different here for both models. Can you share your benchmarks? anything anyone tested.
- 23
- 24
@frog_omo Β·
you can run chatgpt on your laptop without internet. no subscription. no API. no data leaving your machine. here's the 15-minute setup: step 1: download an app pick one: β LM Studio (recommended for beginners) β Jan β GPT4All β Ollama + Open WebUI (if you want browser interface) step 2: download a model start with one of these: β Llama 3.2 3B β best all-rounder for laptops β Qwen 2.5 3B β great for writing β Gemma 2 2B β fastest, smallest β Mistral 7B β best quality (needs 16GB RAM) step 3: start chatting that's it. no account. no API key. what "3B" and "7B" mean: 3B = 3 billion parameters = runs on 8GB RAM 7B = 7 billion parameters = needs 16GB RAM smaller = faster but less capable larger = smarter but slower what local models handle: β summarising documents β drafting emails β brainstorming ideas β explaining code β everyday writing what they don't handle: β complex reasoning β current events (no internet) β tasks requiring GPT-4 level thinking why run AI locally: β privacy β nothing uploaded anywhere β offline β works on planes, bad wifi, anywhere β free β no monthly subscription β unlimited β no rate limits my recommendation: download LM Studio β install β search "Llama 3.2 3B" β download β chat fifteen minutes from now you'll have a private AI assistant that works offline. your data never leaves your laptop.
- 25
- 26
@TheCraigHewitt Β·
Getting local AI models set up is easier than you think. In this video I compare Ollama to LMStudio as well as explore the newest open weight models like Gemma 4 and Qwen 3.5. Local models are just getting really good, and I think can replace 50% of what you're doing with frontier models like Opus 4.6 and GPT 5.4 And they're just getting better, getting smaller, and easier to run.
Watch video
- 27
- 28
- 29
@WellerOlaf Β·
Running Qwen 3.5 9B locally on my ThinkPad P14s (Quadro T500) via LM Studio. Pretty impressive what open-source models can do on a laptop now. Speed Iβm seeing: ~5 tok/s for simple prompts ~1.4 tok/s for harder reasoning tasks Test prompt: A bat and a ball cost $1.10 together. The bat costs $1 more than the ball. How much does the ball cost? Explain your reasoning.
Best Tweets by Topic