Santiago Rodríguez Díaz

Data Scientist

[ollama @ollama]

Gemma 4 Quantization-Aware Training (QAT) weights are now available on Ollama!

They reduce memory requirements while maintaining model quality.

E2B:
ollama run gemma4:e2b-it-qat

E4B:
ollama run gemma4:e4b-it-qat

12B:
ollama run gemma4:12b-it-qat

26B:
ollama run gemma4:26b-a4b-it-qat

31B:
ollama run gemma4:31b-it-qat

Try them with ollama launch integrations to use with your favorite tools 👇👇👇

[Ehsan @acadictive]

Dear GitHub Copilot team,

I am happy to announce that I successfully burned all of my monthly tokens in under 3 days thanks to your garbage new pricing model.

I'd also like to inform you that I won't be renewing my subscription or adding more budget.

Best,
A former customer.

[Santiago Rodríguez Díaz @sonriks6]

@LyalinDotCom @ollama Only MLX for the moment… 😭

[Santiago Rodríguez Díaz @sonriks6]

@NVIDIAGeForce #RTXon Control Ultimate

[Santiago Rodríguez Díaz @sonriks6]

@2010MisterChip Los patrocinadores estarán que trinan por las audiencias, jajajaja

[Santiago Rodríguez Díaz @sonriks6]

@2010MisterChip Horrible, me he perdido el partido!!

[Santiago Rodríguez Díaz @sonriks6]

@NVIDIAAI @grok explain this

[Santiago Rodríguez Díaz @sonriks6]

@witcheer The price of ‘freedom’ an investment of 3000+$ and monthly electricity bill 50-60$ to keep this machine alive 24/7 to run an open weight model? Does anyone see this? I know there are many advantages but there’s no break even point compared to cloud providers!

[Warp @warpdotdev]

You can now bring your own key and inference endpoint to the Warp Agent, no paid plan required.

[Santiago Rodríguez Díaz @sonriks6]

.@openclaw I've migrated to @NousResearch Hermes Agent. full_stop.

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[Santiago Rodríguez Díaz @sonriks6]

@witcheer Why don’t you run qwen3.5:4b with a decent ctx? It runs full on 8 Gb and is not that ‘dumb’ with pi coding harness

[Santiago Rodríguez Díaz @sonriks6]

@AishwaryaDevv I’ve just dropped Hermes and OpenClaw was about to do it… If you need a coding harness used Codex/Claude Code period, if you want a personal assistant cool and fancy then fight against the two first

[Santiago Rodríguez Díaz @sonriks6]

@hgruenhagen @openclaw node-llama-cpp and whatever model it sets when you define ‘local’

[Santiago Rodríguez Díaz @sonriks6]

@petergyang I’m more lean towards OpenClaw the level of effort from devs will come back with stability and reliability soon \ In the long run OC will lead

[Santiago Rodríguez Díaz @sonriks6]

@KarenPayneMVP GPT5.4 as main, Opus for long-term plans

[Santiago Rodríguez Díaz @sonriks6]

@NoahKingJr To me there’s no ‘race’ or at least we are far from the finish. Indeed a loser now would be dramatic, we need a balanced share of usage

[Santiago Rodríguez Díaz @sonriks6]

@xdadevelopers You are not using it well, add instructions, skills, hooks and prompts. Use it with vscode and gh copilot and repo-memory and then see the real difference

[Santiago Rodríguez Díaz @sonriks6]

@Bhavani_00007 VScod4ever!

[9to5Linux @9to5linux]

GNOME 51 “A Coruña” Desktop Environment Is Scheduled for September 16th, 2026 https://t.co/3IJIBqo99y

@gnome #Linux #OpenSource