@OrganicGPT same experience. gemma4 31b dense bf16 > same qwen3.6 for my usage (hermes, chat, my apps). have you tried quantized ? i'm shocked - same perf for the way I use. https://t.co/V93S3aFrq8
We just dropped Gemma 4 Quantization-Aware Training (QAT) checkpoints on Hugging Face!
All Gemma 4 model sizes and their drafters are now optimized with QAT to cut memory requirements and maximize on-device performance!
@jenzhuscott I did personal app, only I use. Also clone of a game from google play without ads and other limits for my family, plus added multiplayer mode missing in the original one. not going to sell anything.
@MrPeterLMorris /btw, check @digitalix yt videos how to replace 1tb ssd with 4tb, and moving to faster bus. you can save simply by replacing + if you sell 1tb - more
Clearly, Google Omni has been wildly underrated.
Here it's turning a normal human hand into a live anatomy demo! Letting you see the muscles, tendons, and cartilage as if the skin were removed.
Brilliant for educational purposes!
I just sequenced a human genome to 30× coverage entirely at home.
As far as I know, this is the first time this has been done.
I didn’t step foot in a lab once. Every step - from saliva collection, to running the sequencer - took place in a single room with a dining table + kitchenette.
Six weeks ago, I had never done wet lab biology before.
I used an Oxford Nanopore P2 Solo - the only commercially available sequencing device portable enough to do 30x human genome sequencing at home.
Biggest takeaway - I could build something that combined software, hardware, and molecular biology far faster than I thought was possible.
I can name >100 specific instances where AI helped me solve a technical problem that would previously have blocked me because I lacked access to a domain expert.
For example: how do I save my sequencing run when my DNA extraction yield is 4x lower than I need it to be, and I have this limited set of reagents to hand?
To make this work, I had to navigate multiple disciplines:
- writing software to monitor sequencing runs and orchestrate remote GPU infra for basecalling
- learning + executing 5 hour long molecular biology protocols
- building a hardware device to quantify DNA concentration
Apologies for the hyperbole, but I feel super lucky to be living in 2026.
A few weeks ago I decided to sequence a human genome to 30x at home.
Then I actually did it. And I did it really quickly.
로컬LLM 모델을 잘 활용하는 방법 중 하나 :
사용중인 Codex, Claude에게 스킬을 만들어달라고 합니다.
“앞으로 너는 오케스트레이터고, 로컬LLM은 너의 지시를 따르는 부하야, 로컬LLM은 너보다 멍청하니까 지시를 내릴땐 아주 구체적으로 줘야해, 그리고 앞으로 니가 할 일은 계획을 짜서, 지시를 만들고, 작업물을 평가하는거야.”
이제 당신은 $200 구독에서 $20 구독으로 변경해도 사용한도가 충분합니다.
@bnjmn_marie I switched from qwen3.6 to gemma4 and it was relaxing. almost immediate answers for hermes requests. (comparing sparse models on dgx spark)