architehc

AI Chatbot Innovator | Ex-Google | Quant

[Elon Musk @elonmusk]

The car that used to be in my garage is currently in an Earth-Mars elliptical orbit and will be there for at least 10 million years

[architehc @architehc]

@eastdakota Dayum

[architehc @architehc]

@demishassabis Yes every PC can run it

[Sundar Pichai @sundarpichai]

Our new Gemma 4 12B model hits a sweet spot between size + performance: it can run locally on a laptop, while enabling powerful multi-step reasoning and agentic workflows. Can’t wait to see what the community does with this one!

[architehc @architehc]

@Google @googlegemma Ty google

[Google @Google]

Today we’re introducing Gemma 4 12B — our latest open model that brings advanced agentic reasoning, vision and audio directly to your laptop.

It delivers performance nearing our larger Gemma models with a much smaller total memory footprint, while being small enough to run locally with just 16GB of VRAM. It’s open and accessible for everyone to use under a permissive Apache 2.0 license.

This is all made possible by our new, unified architecture that removes separate multimodal encoders. Here’s how we did it 🧵

[Alok @analogalok]

i just ran Google's brand new Unsloth Gemma4 12B dense GGUF on my RTX 4060 using llama.cpp + CUDA 13.2

21 tokens per second. on a budget consumer GPU. locally.

no API. no cloud. no subscription.

and the benchmarks are absolutely cooked

# first let's talk architecture because this is genuinely different

every multimodal model you've used has a frozen vision encoder + frozen audio encoder + LLM backbone glued together

Gemma 4 12B is different

it's a single decoder only transformer. that's it. vision? raw 48×48 pixel patches → one matmul → projected directly into the LLM

audio? raw 16kHz signal sliced into 40ms frames → linear projection → same LLM input space

no encoder tax. no latency penalty. no fragmented memory

to put the encoder savings in perspective:

old Gemma 4 26B approach:

- 550M param vision encoder (frozen)
- 300M param audio encoder (frozen)
- LLM backbone

Gemma 4 12B:

- 35M param vision embedder (a single matmul)
- no audio encoder at all
- LLM backbone handles EVERYTHING 550M → 35M for vision alone. that's a 15x reduction

this is why the gemma-4-12b-it-Q4_K_M.gguf is just 6.6 GBs!!!

and it has 256K native context context

# Benchmarks:

AIME 2026 (math olympiad): 77.5%
GPQA Diamond (expert science): 78.8% LiveCodeBench v6 (real code): 72%
Codeforces ELO: 1659
MMLU Pro: 77.2%
MATH-Vision: 79.7%
BigBench Extra Hard: 53%

inference → llama.cpp, LM Studio, vLLM, SGLang

llamacpp flags:

-m "gemma-4-12b-it-Q4_K_M.gguf" -ngl 99 -c 8000 -v --port 8080

Available on huggingface now! Link below

[Google Gemma @googlegemma]

Meet Gemma 4 12B!

A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license.

Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇

[architehc @architehc]

@coinbureau Windows? Nah

[Arkhai @arkhai_io]

Today we're launching Simple Compute Market (SCM).

The market is simple: agents find compute, negotiate, settle, and get access without a human driving every step.

Open-source. Agent-driven. Public good. No token. No fees.

[architehc @architehc]

@elonmusk https://t.co/krPbtmNVvy is the big unlock in ptx

[elie @eliebakouch]

"/goal rewrite jax in rust"

[Yuchen Jin @Yuchenj_UW]

Whoever invented “Member of Technical Staff” was a genius.

It filters out Staff/Principal title-maxxers, protects engineering and research from corporate ladder brain, and leaves recruiters staring at LinkedIn like: “Is this person L4 or L7?”

MTS is the best title. Happy to be MTS.

[Pyth Network 🔮 @PythNetwork]

NEWS: Pyth Core is getting an infrastructure upgrade on July 31 📢

But one important change: All Pyth Price Feeds API access will require a Starter or Pro subscription.

More subscriptions → more revenue → more PYTH purchases

Everything you need to know 🧵

[crocodile @crocodilecrisis]

i’d like for this vid to be erased forever, thank you.

[Mario Nawfal @MarioNawfal]

🇭🇷 Picasso Pizza in Split, Croatia has been testing drone deliveries right to the table.

The future is here, and it’s delicious!

[Goodfire @GoodfireAI]

Neural networks do math by rotating shapes.

We found a shape-rotating calculator hidden inside an LLM – and it’s used for more than just math! (1/6)

[Socket @SocketSecurity]

🚨 UPDATE: Mini Shai-Hulud has crossed from @npmjs into @pypi and is still spreading.

Newly confirmed compromised artifacts:

@​opensearch-project/opensearch: 3.5.3, 3.6.2, 3.7.0, 3.8.0 (1.3M weekly downloads)

mistralai: 2.4.6 on PyPI

guardrails-ai: 0.10.1 on PyPI

additional @​squawk/* packages on npm

guardrails-ai 0.10.1 executes malicious code on import. On Linux, it downloads git-tanstack[.]com/transformers.​pyz, writes it to /tmp/transformers.​pyz, and runs it with python3 without integrity verification.

The git-tanstack.​com domain displayed a message signed “With Love TeamPCP,” along with: “We've been online over 2 hours now stealing creds
Regardless I just came to say hello :^)”

The page also linked to a YouTube video and you can probably guess which one.

[Federico Ulfo @feulf]

@US_Stormwatch @architehc and I did NY Singapore with a layover in Dubai, we went jogging at 5am to beat the jet lag