Super Private AI browser with the local AI Founder: @skinbagwbones
California, USA
- Tweets 510
- Following 59
- Followers 8,159
- Likes 825
Pinned Tweet
Hermes agent running in private browser on free local models
Private by design. Local. Open-source
22
30
268
62,128
Sigma Browser retweeted
Space Bunny Alpha mogged by DeepSeek V4.1 Flash 🐳
We asked both to build Minecraft in one HTML file and DeepSeek V4.1 Flash made a forest biome you can walk and dig in while Space Bunny Alpha's ground has holes showing the sky
Run AI models locally -> atomic.chat
Space Bunny (stealth model) is free for the next week
- 1M Context
- Multi-modal
- Zero Data Retention
24
7
259
45,804
Sigma Browser retweeted
Opus 5.5 destroyed GPT 6 Sol at Blender 3D Pelican 🦩
Both frontier models dropped today so we gave them the same brief to animate a looping 3D pelican on a bicycle in Blender and Opus 5.5 came back with the more charming ride
Run both models via API -> atomic.chat
Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family.
It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
41
37
785
289,981
Sigma Browser retweeted
Local Laya moggs Jev at @grok 4.7-built Tetris 🧩
An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air!
Run AI models locally -> atomic.chat
介绍比Jev快50倍，在你设备上跑的laya-mlx!
只在你的设备上占用最高1G内存
Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统
我将其移植到MLX,并且做了一些性能优化!
视频中就是这个模型在我的本地M3Max上玩贪吃蛇
这个模型能够以每秒决策60次的速度玩贪吃蛇！
github.com/mizorewww/laya-ml…
167
590
6,206
1,029,138
Sigma Browser retweeted
DeepSeek V4.1 Flash made DOOM in Atomic Chat 🐳
@deepseek_ai dropped a new architecture for the flash model so we tested it by making Doom in an html file and it built a real raycasting shooter with gun mechanics and enemy waves
Run AI models locally -> atomic.chat
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient.
🔹 Introducing the smallest model in our new architecture family, with native visual understanding.
🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models.
1/6
3
9
86
29,671
Sigma Browser retweeted
New Fable 5.1 absolutely crushed Fable 5 at making a racing game👾🔥
@claudeai just dropped Fable 5.1, so we gave both models the same prompt to build a playable racing game from scratch in Godot with BlenderMCP
Tasks:
- Make car and environment models using BlenderMCP
- A big map for long driving sessions
- Realistic car handling
- Simple HUD for speed and controls
Outputs:
Fable 5.1: 1.2M tokens, 123.98$, 59.8 minutes
Fable 5: 897K tokens, 95.87, 57.3 minutes
Fable 5.1's models are far more detailed and the game runs smooth, the world feels alive while you drive. Fable 5 finished all three tasks and its HUD and controls work, but its models are plain and the game feels stiff
We’re introducing Claude Fable 5.1 and Claude Mythos 5.1.
They're the world’s most advanced models for coding and knowledge work.
8
7
145
21,567
Sigma Browser retweeted
Run OpenClaw 2.0 through Atomic Chat local LLM server on a 16GB MacBook 💻🦞
We gave OpenClaw a task to edit a video using Gemma 4 E4B, it successfully created a welcome video in two minutes by writing custom React code
Load the model in atomic.chat, start the LLM server and OpenClaw 2.0 picks it right up
9
21
306
44,567
Sigma Browser retweeted
Open-weight Qwen 3.8 2.4T built a Call of Duty clone in one prompt 🪖
@Alibaba_Qwen released the 2.4T Max weights, so we rented a B200 cluster and asked the model to make a Call of Duty clone
Output: ~1.1M tokens · 5 hours · one prompt
Almost no one can run 2.4T at home, luckily there is a 27B version that runs on a 16GB MacBook Air with our Atomic Dynamic quants
We promised open weights for Qwen3.8. Now, time to meet them! 🎉
⚡ Qwen3.8-27B:
- A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows.
- 262K native context, easily extendable to 1M tokens via YaRN.
- Built for builders. Highly efficient, high-quality, and licensed under Apache 2.0.
🚀 The open weights for Qwen3.8-2.4T-A95B (Max-level) have also been released recently.
Whether you're shipping lightweight applications with Qwen3.8-27B locally or building agents with Qwen3.8-2.4T-A95B, they're yours now!
Download, deploy, and build something we haven't imagined yet. 👀👇
- Hugging Face：
huggingface.co/collections/Q…
- ModelScope：
modelscope.cn/collections/Qw…
21
34
408
46,229
Sigma Browser retweeted
New Muse Glimmer 30B destroyed Gemma 4 31B at making retro arcade games!
We gave three models the same task and compared one-shot outputs. Muse Glimmer 30B, Gemma 4 31B and Qwen3.6 27B each ran locally on its own RTX 5090 with 32GB VRAM
Tasks:
- Space Invaders
- Tetris
- Arkanoid with multiball
Outputs:
Muse Glimmer 30B: 83.4K tokens, 17.7 min
Qwen3.6 27B: 23.7K tokens, 5.4 min
Gemma 4 31B: 17.8K tokens, 4.5 min
Glimmer's games play like the originals. The alien fleet speeds up with every kill, the blocks lock and lines clear, the bricks break. Nothing froze or crashed. Gemma broke on Tetris, its bot piles every piece against the left wall until the stack hits the ceiling with half the well empty. Qwen finished all three but some of its Arkanoid balls phase straight through the paddle.
Run Muse Glimmer yourself in Atomic Chat from day 0!
Introducing Muse Glimmer, an open-weight 30B-parameter model optimized for local, always-on agent workflows.
Muse Glimmer delivers strong performance on key agentic use cases and benchmarks compared with leading models in its size category, and is designed to run entirely on consumer hardware like a Mac or PCs with performant GPUs.
In keeping with our long tradition of sharing fundamental AI research, we’re releasing model weights under a permissive Apache 2.0 license.
🧵👇
8
27
197
39,349
Hermes agent running in private browser on free local models
Private by design. Local. Open-source
22
30
268
62,128
@NousResearch @Teknium what do you guys think about this?
17
1,916
Private AI browser with the OpenClaw agent on free local models
Run your agent on Qwen, Gemma, or Nemotron directly in the browser
Open source. Private. Runs on your local device
30
22
222
115,757
Now your AI agent can turn your idea into a video in ONE chat
We just shipped Image To Video inside Sigma Browser 🎬
Write a prompt, the AI generates an image, click Animate Photo – and it comes to life
No animation prompts, no extra tools
The whole thing happens in the same chat where you had the idea
Try it – app.sigmabrowser.com/chat
25
18
158
4,776
Uncensored AI. Running locally. Inside your browser.
In Sigma you can chat with your own local LLM directly in the browser.
The model runs entirely on the user's machine and is fully open-source. No external APIs, no cloud processing - all interactions stay local.
Both censored and uncensored versions are available.
Try it out now
sigmabrowser.com/local-ai-ch…
34
27
157
5,789
Our referral program update is LIVE!
Invite your friends to join Sigma and earn $SIGMA for every successful referral.
We have simplified the whole flow, so it is now faster and easier than ever.
The video below shows exactly how to do it.
P.S. whitepaper release next week ;)
35
25
153
8,059
A token should do more than exist
It needs real utility to stay valuable and relevant to people
Our token powers 3 core functions of the network:
• Staking - hold and stake a certain amount of tokens to unlock an AI chat subscription, while also earning token rewards for staking
• Governance - participate in key protocol decisions and help shape the future of the network
• Device Resource Farming - contribute your device’s resources and earn tokens through a farming model. As more users participate, this creates a collectively powered, decentralized AI network
Browse to earn:
Join our bounty program to become one of the first holders of $SIGMA
lyrical-handspring-d4f.notio…
56
50
240
10,143