Atomic Local Ai Agent

Multi chain staking operator, trusted by over 200,000 delegators since 2019

[Atomic Local Ai Agent @AtomicNodes]

Atomic chat on Hugging face!

We're officially a Local App on the world's biggest AI hub. Run 180,000+ open-weight models from @ huggingface on your local device!

[atomic.chat @atomic_chat_hq]

New Google Gemma 4 12B claims near-26B performance - we tested both!

We ran both models locally on one RTX 4090 and gave each the same task: write a self-contained HTML5 canvas animation with real physics in one file without libraries. Three scenes - a Galton board, two blocks colliding off a wall, and a chaotic triple pendulum

Outputs:
Gemma 4 26B-A4B: 15 GB VRAM usage, 6.9k tokens, 138 tok/s
Gemma 4 12B: 9 GB VRAM usage, 8.9k tokens, 80 tok/s

Same Gemma 4 family, but the 26B-A4B won every scene and ran ~1.7x faster - on just 4B active params. The 12B stayed very close though, on almost half the VRAM - which makes it the ideal model for a 16 GB laptop

[Atomic Local Ai Agent @AtomicNodes]

New Google Gemma 4 12B claims near-26B performance - we tested both!

We ran both models locally on one RTX 4090 and gave each the same task: write a self-contained HTML5 canvas animation with real physics in one file without libraries. Three scenes - a Galton board, two blocks colliding off a wall, and a chaotic triple pendulum

Outputs:
Gemma 4 26B-A4B: 15 GB VRAM usage, 6.9k tokens, 138 tok/s
Gemma 4 12B: 9 GB VRAM usage, 8.9k tokens, 80 tok/s

Same Gemma 4 family, but the 26B-A4B won every scene and ran ~1.7x faster - on just 4B active params. The 12B stayed very close though, on almost half the VRAM - which makes it the ideal model for a 16 GB laptop

[atomic.chat @atomic_chat_hq]

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👇

[atomic.chat @atomic_chat_hq]

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 👇

[Atomic Local Ai Agent @AtomicNodes]

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. Run tests on a MacBook Pro M5 max. Gemma 26B with MTP drafts tokens 40% faster. Source code and models below👇

[Atomic Local Ai Agent @AtomicNodes]

Multi-Token Prediction (MTP) for LLaMA.cpp!

Running Gemma4 local model significantly faster.

We patched llama.cpp. Quantized Gemma 4 assistant models for GGUF format. Run test on a MacBook Pro M5 max. Gemma 26B with MTP drafts tokens 40% faster. Source code and models below👇

[Atomic Local Ai Agent @AtomicNodes]

Multi-Token Prediction (MTP) for Llama.cpp! Running Gemma4 local model 40% faster.

We patched llama.cpp. Quantized Gemma 4 assistant models for GGUF format. Run test on a MacBook Pro M5 max. Gemma 26B with MTP drafts tokens 40% faster. Source code and models below

[Atomic Local Ai Agent @AtomicNodes]

Multi-Token Prediction (MTP) for Llama.cpp!

Running Gemma4 26B local model 40% faster.

We patched llama.cpp. Quantized Gemma 4 assistant models for GGUF format. Run test on a MacBook Pro M5 max. Gemma 26B with MTP drafts tokens 40% faster. Source code and

[Atomic Local Ai Agent @AtomicNodes]

Introducing MTP for Llama.cpp! Running Gemma4 local model 40% faster.

Multi-Token Prediction gives significant speedup, without quality degradation. Instead of predicting one token at a time, MTP drafts several in parallel.

[Atomic Local Ai Agent @AtomicNodes]

Introducing Multi-Token Prediction (MTP) for Llama.cpp!

Multi-Token Prediction gives significant speedup, without quality degradation. Instead of predicting one token at a time, MTP drafts several in parallel.

We patched llama.cpp. Quantized Gemma 4 assistant models for GGUF format. Run test on a MacBook Pro M5 max. Gemma 26B with MTP drafts tokens 40% faster.

[Atomic Local Ai Agent @AtomicNodes]

Introducing Multi-Token Prediction (MTP) for Llama.cpp! Running Gemma4 local model 40% faster.

We patched llama.cpp. Quantized Gemma 4 assistant models for GGUF format. Run test on a MacBook Pro M5 max. Gemma 26B with MTP drafts tokens 40% faster.

Source code and

[atomic.chat @atomic_chat_hq]

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

[Atomic Mail @atomic_mail]

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.

[Atomic Local Ai Agent @AtomicNodes]

Download MacOs app or run in cloud https://t.co/8ibfBRGkW4

[atomicbot.ai @atomicbot_ai]

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👇

[atomicbot.ai @atomicbot_ai]

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!

[atomic.chat @atomic_chat_hq]

Run OpenClaw with Gemma 4 and Atomic Chat

MacBook Air M4 · 16 GB RAM · 25 tok/s

No cloud! No subscription fees! Open-source local model. Runs on your regular device

[atomicbot.ai @atomicbot_ai]

Running OpenClaw with Gemma 4🦞

Free Open Source Local Model

Device: MacBook Air M4 16Gb