Building @atomic_chat_hq Local AI previously @AtomicWallet 15M users
Joined June 2009
- Tweets814
- Following631
- Followers7.3K
- Likes2.8K
Konstantin Gladych retweeted
Run Qwen3.8 27B locally via Atomic Chat💥
We released Atomic Dynamic GGUF quants, from 8-bit (28.9 GB) down to 1-bit (8.5 GB), and measured all other Qwen3.8 GGUFs in the community
AD-IQ3_S runs on a 16GB MacBook Air and picks the same next token as the BF16 original 92.4% of the time
ALT Quality vs size chart and hardware table for Atomic Chat's Qwen3.8 27B GGUF quants. The chart plots mean KL divergence vs BF16 against file size for every Qwen3.8 27B GGUF in the community: the blue AtomicChat AD line runs from 8.5 GB to 28.9 GB, with unsloth, lmstudio-community and ggml-org files as separate markers, and shaded zones showing where each side is closer to BF16. Measured on eval_neutral held-out, 4096 ctx, reference BF16, 4x RTX 5090, CUDA 13.0. The table below recommends a quant per memory size: 12 GB takes AD-IQ2_XS at 9.9 GB with top-1 83.5%, 16 GB takes AD-IQ3_S at 13.8 GB with 92.4%, 24 GB takes AD-Q5_K at 20.2 GB with 97.3%, 32 GB takes AD-Q6_K at 25.0 GB with 98.7%, and 48 GB takes Q8_0 at 28.9 GB with 98.9% and mean KL divergence 0.0006.
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…
Konstantin Gladych retweeted
Run DeepSeek V4 Flash 0731 locally 🐳
We released 14 quants on Hugging Face, from lossless BF16 to 1-bit
AD-IQ2_M is the best fit for 128GB hardware. It matches the original's token choice 83.6% of the time, measured against all other V4 Flash GGUFs in the community
🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta!
🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇
🔷 The official V4-Flash now natively supports the Responses API format and is fully adapted for Codex!
Check out the configuration details in our official API docs: api-docs.deepseek.com/quick_…
Konstantin Gladych retweeted
Atomic Chat is now on Hugging Face 🤗
We're officially a Local App on the world's biggest AI hub. Run 200,000+ open-weight models from @huggingface directly on your device - private, local, and open source!
Konstantin Gladych retweeted
We released iOS app for Hermes Agent 📱
Connect to your self-hosted agent over Tailscale, Cloudflare Tunnel or ngrok. Or deploy on a VPS. Run tasks and manage your agent from anywhere.
Konstantin Gladych retweeted
MTP speedup Qwen by 2.5x in Atomic Chat
Dense vs MoE models on 2x RTX 5090
Qwen3.6 27B: 51 → 117 tps +137%
Qwen3.6 35B-A3B: 218 → 267 tps +25%
MTP drafts several tokens ahead and verifies them in one pass. The speedup depends on memory moved per pass. Dense 27B reads all 27B params per token, MoE 35B-A3B only reads 3B active. Dense had way more to save by batching.
The baseline tps also differ (218 vs 51) for the same reason from the other side. Token generation is memory-bandwidth bound, and MoE moves ~8x less memory per token, so its baseline is already 4x ahead.
~80% draft acceptance. Zero accuracy loss. ~1 GB extra VRAM.
Open-source code and local AI app – in the comments 👇
Konstantin Gladych retweeted
Hermes Agent vs OpenClaw using Qwen 35B Local Model
We asked agents to scrape GitHub star history for both tools, find what caused the growth spikes, build a live dashboard in the browser.
MacBook Pro M5 Max 64Gb
OpenClaw: 203k tokens, 12m 01s - wrote a bash script
Hermes: 257k tokens, 33m 01s - wrote a SKILL.md
OpenClaw hit GitHub API, got truncated responses, paginated through contributors, pulled star-history JSON, found a security incident in OpenClaw's history, fetched SVGs, fixed broken HTML from trimming, rewrote it clean.
Hermes parallel tool calls across GitHub API, web search, and browser. Hit Google rate limit, auto-switched to DuckDuckGo. Fetched article contents, mapped viral moments, then built the dashboard.
Both shipped a live dashboard with star growth charts and spike annotations
Konstantin Gladych retweeted
Multi-Token Prediction (MTP) for Qwen on LLaMA.cpp!
+40% performance! 90% acceptance rate. Running locally on a MacBook Pro M5 Max 64GB
We patched LLaMA.cpp, quantized Qwen 3.6 27B into GGUF format with TurboQuant and shipped MTP drafts on top. Benchmark, Source code & models👇
Konstantin Gladych retweeted
Meet the 1st radio on X fully run by AI. Covers AI news 24/7, always on. Designed for builders and founders. Live right now.
AI Twitter is hundreds of posts an hour. You can't read all of it.
Tune in - hit play - do your thing. With non-distracting ambient music between segments.
What you'll hear any hour you tune in:
- breaking news within minutes
- roundups every 30 min — top stories with builder context
- startup funding & traction radar
- what's moving and trending in AI tooling — GitHub, OpenRouter, HuggingFace — every 30 min
- community — what people actually say on X, HN, YouTube
- editorial takes — and real opinions from founders, researchers, builders
- patterns others miss, delivered as arguments with conclusions
Five AI hosts. Each with their own editorial judgment, memory, and personality. They don't just read data — they collect patterns, find contradictions, form opinions, and argue their point.
And they do it live, continuously, on air.
Konstantin Gladych retweeted
Hermes agent running in private browser on free local models
Private by design. Local. Open-source
Konstantin Gladych retweeted
Multi-Token Prediction (MTP) for LLaMA.cpp!
Running Gemma4 local model 1.5x faster.
We patched LLaMA.cpp. Quantized Gemma 4 assistant models into GGUF format. We ran tests on a MacBook Pro M5Max. Gemma 26B with MTP drafts tokens 40% faster. Benchmarks, source code and models 👇
Konstantin Gladych retweeted
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
Konstantin Gladych retweeted
HOLY MOLY running a 35B model locally on a MacBook shouldn’t be THIS FAST 🤯
Spent my weekend in @atomic_chat_hq testing Qwen 35B vs. Qwen 27B on my local machine.
I had them generate a fully animated HTML/Canvas car mini-game (demo below),
... and both models breezed through the physics and parallax scrolling without a hitch!
The secret sauce here is the Atomic Chat app.
Because it's perfectly optimized for Mac and uses Google's new TurboQuant under the hood, you can run heavy open-source models flawlessly while keeping top-tier output quality 👊
Other perks:
→ ZERO setup required
→ Access 1,000+ models completely free
→ 100% offline and private
→ Zero API limits
... and MUCH more!
I dropped the prompt I used in the 🧵↓
Spin it up locally and let me know what you get!
Konstantin Gladych retweeted
Deepseek V4 Pro vs GPT-5.5 in a gamedev contest (full prompt is below)🏎️
Cost:
Deepseek V4 Pro: $0.07656
GPT-5.5: $0.33063
Output stats:
Deepseek: 34 tok/s · 9m 5s · 18,869 tokens
GPT-5.5: 25 tok/s · 7m 5s · 10,580 tokens
Conclusion: GPT-5.5 clearly made the better karting game. Deepseek V4 Pro was 4.3x cheaper and generated almost 2x more tokens, but the final result was weaker. It struggled with graphics, visual polish, and creative direction, while GPT-5.5 delivered better game quality, better visuals, more creativity, and stronger overall execution. Even though Deepseek positions itself as a strong model for coding, in this gamedev test it still felt far behind GPT-5.5.
Try the same karting prompt with another AI model and share your result below.
Konstantin Gladych retweeted
We teamed up with @NanoClaw_AI to provide local models for your agents
Run personal agent with NanoClaw locally on your device via Atomic Chat MCP
Free Open Source: Gemma, Qwen already live in NanoClaw!
Konstantin Gladych retweeted
Compared Qwen3.6 35B and 27B in the same conditions with Google TurboQuant
Device: MacBook Pro M5Max 64GB RAM
Outputs characteristics:
Qwen3.6 35B: 6672 tokens, 2m 10s, 65 tok/s
Qwen3.6 27B: 7344 tokens, 5m 22s, 24 tok/s
Conclusion: Both models were asked to draw waves using HTML, 35B responded quickly but the result feels weak and messy, while 27B took more time and delivered a much cleaner and more consistent result, because it is built for thinking and planning, so it works better on tasks that need structure, overall 27B is a better choice for tasks where planning matters, while 35B is more suitable for everyday use when you just need a fast response
Konstantin Gladych retweeted
Google Chrome invited Atomic Mail to test how the built-in @GeminiApp can improve private email.
Now you can run Atomic Mail AI features with Local Models on your device:
– 100% private
– Your data stays on your laptop
– Zero cost
Joint case study with @ChromiumDev coming soon – follow us!
Guide + link in the comments.
Konstantin Gladych retweeted
Hermes Agent by @NousResearch (100k+ ⭐) now inside Atomic Bot:
– Free Local models: Qwen, Gemma or
– Use your API keys for any provider
– Dashboard, terminal, logs and files explorer
– Private and Open Source
Download MacOS app or run in Cloud👇
Konstantin Gladych retweeted
You can run Hermes agent by @NousResearch with Kimi K2.6 on @atomicbot_ai VPS 🌑
@Kimi_Moonshot just dropped a new open source coding model. We asked Hermes to build and deploy a game. It did incredibly well!
Konstantin Gladych retweeted
Kimi 2.6 from @Kimi_Moonshot is here - and 0 day available on AI/ML API!
It is insanely powerful - we asked it to build space invaders and one shot result was stunning.
You can check out the prompt in comments.