Top Tweets for #LocalLLM
Day 2 of Genesis Lab: my local models are talking to each other.
Qwen3.8-27B (vLLM) → local image job → verified PNG. 5 turns, 42 s incl. render, all on 2× RTX PRO 6000. Ran through OpenCode 1.19.4; the OpenCode 2 cutover is next.
What should Genesis run next? 👇
#LocalLLM #GenesisBuild
@ollama @trychroma @hacktoberfest 🔗 Demo: https://t.co/yDoz9alsnK
⭐ GitHub: https://t.co/DXNsKCKMzp
🌐 https://t.co/ynddrTv9M1
Local AI vs cloud LLMs for sensitive legal data: what's your take?
#LocalLLM #PrivacyFirst #OpenSource
🚀 A 35B model fits a 16 GB M4 Mac mini
Qwen3.6–35B runs fully in memory — one command, offline, no drive streaming.
New compression: 70 GB → 9.4 GB. ~10 tokens/sec, free, private.
https://t.co/UYMpiGOerm
#LocalLLM #AppleSilicon #AI
Mac Studioの512GBメモリ、日本の値段が出ました。1TB構成で3,973,800円になり、96GBからの追加だけで279万円です。
動かすモデルが256GBに収まるなら、512GBまで行く理由はほとんどなさそうです。
https://t.co/w5ZfzjOW8O
#MacStudio #M5Ultra #Apple #Mac #LocalLLM
Take away autocomplete for 20 minutes and watch panic set in.
AI coding assistants are a superpower, right up until the Wi-Fi drops—unless your coding model runs locally on your own machine.
More local AI breakdowns on YouTube (@NxTLvLTech)
#AI #LocalLLM #NxTLvLTech
Monthly AI Subscription Audit and Privacy Basics
AI disclosure: this video uses an AI-generated avatar of…
AI disclosure: this video uses an AI-generated avatar of Mark and a cloned version of his voice.
Full breakdown on YouTube (@NxTLvLTech)
#AI #LocalLLM #NxTLvLTech
I've open-sourced "Deinei (泥濘)" on GitHub (MIT)!
A local LLM companion system uniting long-term memory RAG, KV cache preservation (within 16K ctx), 3D VRM / Live2D rendering, and 24kHz zero-shot TTS in a single launcher.
https://t.co/FYfAFaBjOM
#LocalLLM #llama_cpp #VRM
763.2B DeepSeek V4.1 Flash GGUF now runs on 12GB VRAM; if you already downloaded, the update is just 80 KB. ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF #AI #LocalLLM #OpenSource #GGUF #Quantization
siliconshelf now lists 493 on-device ai apps for iphone, ipad and mac.
new on the shelf: Pipette by Liquid, Kodo, Transcribee, Airgap: Private AI Chat and RAMDeck.
filter by offline, open source, MLX or GGUF:
https://t.co/YjqBLONUwd
#LocalLLM #OnDeviceAI
かなり介護が必要で、作れるものもちょっとづつではあるが、いちおう動くものは作れた。
Opencode+LMStudio (Qwen3.6-35B-A3B/x68code)
自機だして、弾撃つだけで一苦労だ。
まぁ無限にトークン使えるからぽちぽちやるにはいいのかもしれない。
#LocalLLM #X68000プログラミング
At night I place my own number, not the crowd's. Where do you place yours? #LocalLLM
Giant Qwen on Your Game Card
AI disclosure: this video uses an AI-generated avatar of Mark and a cloned…
AI disclosure: this video uses an AI-generated avatar of Mark and a cloned version of his voice.
Full breakdown on YouTube (@NxTLvLTech)
#AI #LocalLLM #NxTLvLTech
Most Popular Users
Elon Musk 
@elonmusk
241.5M followers
Barack Obama
@barackobama
118.8M followers
Cristiano Ronaldo
@cristiano
114.5M followers
Donald J. Trump
@realdonaldtrump
111.9M followers
Narendra Modi
@narendramodi
107.1M followers
Rihanna
@rihanna
98.7M followers
NASA
@nasa
92.3M followers
Justin Bieber
@justinbieber
91.8M followers
KATY PERRY
@katyperry
90M followers
Taylor Swift
@taylorswift13
84M followers
Lady Gaga
@ladygaga
75.5M followers
Virat Kohli
@imvkohli
73.5M followers
Kim Kardashian
@kimkardashian
70.9M followers
YouTube
@youtube
68.8M followers
Neymar Jr
@neymarjr
66.5M followers
Bill Gates
@billgates
65.3M followers
Selena Gomez
@selenagomez
63.1M followers
The Ellen Show
@theellenshow
62.2M followers
CNN
@cnn
61.7M followers
X
@x
60.7M followers