Kadir

9.4K posts

Kadir banner
Kadir

Kadir

@kad1r

Full Stack Developer - Experienced on #dotnetcore #vuejs #javascript https://t.co/AUvFWR4u8m

Izmir, TURKEY Katılım Şubat 2009
1.3K Takip Edilen713 Takipçiler
Kadir
Kadir@kad1r·
Claude design cidden çok iyi. Figma vs bitmiş olabilir. Prompt'ta çok detay vermesen bile çok iyi tasarım çıkarıyor.
GIF
Türkçe
0
0
1
35
Kadir retweetledi
Aesthetics 𝕏
Aesthetics 𝕏@aestheticsguyy·
Reminder to connect with nature
Aesthetics 𝕏 tweet media
English
25
586
6.1K
109.2K
Kadir
Kadir@kad1r·
🚀 Windows için workspace yöneticisi: 🪟Çoklu workspace, grid layout 🖥️Windows Terminal / PowerShell / cmd 📁Dosya gezgini ⚡Crash recovery 🌍12 dil Apptorium Workspaces ve Powertoys'dan ilham alarak kendi kullanım tarzıma göre bir uygulama yaptım. github.com/kad1r/develope…
Türkçe
0
0
1
66
Kadir
Kadir@kad1r·
@eserozvataf Su gibi içiyor gerçekten. Ollama cloud geçmek sanki daha mantıklı gibi ama henüz deneme şansım olmadı. Denersem buradan da yazarım. Kimi 2.6 baya iyi diyorlardı.
Türkçe
1
0
0
351
Eser Özvataf | SW³
Eser Özvataf | SW³@eserozvataf·
Opus 4.7 ile birlikte 1M context'in kaşla göz arasında kaybolması peki? :)
Türkçe
6
0
47
16.8K
Kadir retweetledi
Curious Minds
Curious Minds@CuriousMindsHub·
Your brain is programmable.
Curious Minds tweet media
English
10
535
2.8K
68.6K
Kadir retweetledi
seyithan
seyithan@seyithanmkl·
seyithan tweet media
ZXX
0
1.6K
8.6K
94.8K
Kadir retweetledi
Graeme
Graeme@gkisokay·
The Local LLM Cheat Sheet for your 32GB RAM device I was asked to put together a practical lineup of local models that fit comfortably on a 32GB machine. At this tier, you start getting access to real flagship-class local models, plus a growing number of custom quants. But for most people, these are the core models worth knowing first. Flagship Models Qwen3.5 27B / GGUF / Q6_K_M The best overall 32GB flagship. General chat, writing, research, and agent workflows. Great if you want one model that can handle almost everything well. Qwen3.6-35B-A3B / GGUF / UD-Q4_K_M Best MoE flagship. Stronger for coding, reasoning, and tool use than most smaller generalists. Gemma 4 31B / GGUF / Q6_K_M Dense premium model. Writing, analysis, reasoning, and high-end local chat. Heavier than the MoE options, but excellent when quality matters more than speed. Models for Fast Flagship Use Gemma 4 26B A4B / GGUF / Q6_K_M Great balance of speed and quality for general assistant work, coding, agent tasks, and research. This is one of the best 32GB picks if you want something that feels high-end without dragging. DeepSeek-R1 Distill Qwen 32B / GGUF / Q4_K_M Offline reasoning engine. Best for math, logic, deliberate analysis, and step-by-step problem solving. Mistral Small 24B / GGUF / Q6_K_M Tool-calling specialist. Strong for assistants, chat workflows, local business tasks, and function calling. Available for 24GB machines. Models for Companion Use Qwen3.5 9B / GGUF / Q6_K_M Best sidekick. Fast drafts, search loops, cheap retries, and secondary agent work. Even on a 32GB machine, you still want a smaller model around for support tasks. Llama 3.1 8B / GGUF / Q6_K_M Long-context companion. RAG, doc ingestion, codebase chat, and long prompts. The output quality is not the sharpest anymore, but it is still useful when needing simple tasks fast. From what my community tells me, the best single models are Qwen3.5 27B or Gemma 4 31B. For two models, the strongest general pairing is Qwen3.5 27B + Qwen3.5 9B. If you are more code-heavy, Qwen3.6-35B-A3B + Llama 3.1 8B. Let me know what models you are running on 32GB, and which ones have actually been worth the RAM.
Graeme tweet media
Graeme@gkisokay

The Local LLM cheat sheet for your 16GB RAM device I pulled together a lineup of small models that can run comfortably on a Mac Mini or personal laptop while still leaving room for context without melting your machine. Models for Daily Use Qwen3.5 9B / GGUF / Q4_K_M Daily driver. General chat, drafting, research, translation. If you're keeping only one, keep this. DeepSeek-R1 Distill Qwen 7B / GGUF / Q4_K_M Reasoning engine. Math, logic, step-by-step problems. Slower, but worth it when you need actual thinking. Models for Specialty Work Qwen2.5 Coder 7B / GGUF / Q4_K_M Code specialist. Completions, refactors, debugging, repo Q&A. Better than a generalist when the task is code. Llama 3.1 8B / GGUF / Q4_K_M Long context worker. RAG, doc chat, codebase Q and A. The output isn't top tier, but the context is strong for its size. Phi-4 Mini Reasoning / GGUF / Q4_K_M Compact thinker. Logic, structured answers, math, and short coding bursts. Smaller context is the catch. Models for Efficiency Gemma 4 E4B / GGUF / Q4_K_M Light all-rounder. Writing, chat, light agents, structured output. Phi-3.5 Mini / GGUF / Q5_K_M Pocket sidekick. Summaries, extraction, background doc chat. Easy to pair with a bigger model. Qwen3.5 2B / GGUF / Q4_K_M Useful for summaries, tagging, rewrites, and lightweight sidekick work. Micro Models Qwen3.5 0.8B / GGUF / Q5_K_M Classification, keyword routing, binary decisions, triage. Gemma 4 E2B-it / GGUF / Q4_K_M Lightweight chat, quick Q and A, summaries, tiny agents. My personal choice for a single model is Qwen3.5 9B For two models use Qwen3.5 9B + Qwen2.5 Coder 7B for code, or Qwen3.5 9B + Phi-3.5 Mini for support tasks. Let me know in the comments your experience with these models, or any I have left out.

English
85
348
2.1K
306K
Kadir retweetledi
Anime Shots
Anime Shots@anime_shots·
This scene was absolutely peak
English
14
248
2.1K
57.7K
Kadir retweetledi
Erdal Yanbuloğlu
Erdal Yanbuloğlu@qujunil·
Okullarda doğru düzgün spor yok; müzik yok, yabancı dil yok, resim yok, tiyatro yok. Eleştiri yok, edebiyat yok. Doğayla, tarihle, toplumla kurulan sahici bağlar yok. Yerine, leş gibi bir sınav düzeni, yalancı ilişki ağı ve eşitsizliğin rutin hali var.
Türkçe
241
4.6K
29.8K
447.6K
Kadir retweetledi
Stefan Đokić | .NET
Stefan Đokić | .NET@TheCodeMan__·
"Aspire is only for .NET apps." I keep hearing this. It's wrong. I built a demo with: → 2 .NET APIs → 1 React + TypeScript frontend → 1 Python background worker → PostgreSQL and Redis All orchestrated from a single Aspire AppHost. The AppHost happens to be written in .NET, but it orchestrates ANY language. The Python worker gets its environment variables injected automatically. The React app gets npm install and npm run dev handled for it. All services appear in the same dashboard. Same logs. Same traces. Same health checks. 3 languages. 1 command. 1 dashboard. I wrote a full beginner's guide with diagrams and code: thecodeman.net/posts/aspire-f… ___ 📌 Don't miss the next newsletter issue, 20,000 engineers will read it, join them: thecodeman.net ♻️ Repost to others. 📂 You can save this post for later, and you should do it. ➕ Follow me to learn .NET and Architecture every day.
Stefan Đokić | .NET tweet media
English
2
9
62
1.8K
Kadir retweetledi
Anooshirvan Miandji
Anooshirvan Miandji@miandji·
Bir toplumun ahlakını ne bozar? Negatif seleksiyon bozar. Peki, negatif seleksiyon nedir? İyiyi cezalandırmak, kötüyü ödüllendirmektir. Yalaka, fırsatçı, paragöz olanın önünü açıp rol model göstermek; dürüst, çalışkan, bilgili olanı engellemektir.
Anooshirvan Miandji tweet media
Türkçe
29
1.2K
3.2K
46.7K
Melis ✨
Melis ✨@ffmelis·
Tüm tişörtlerin önünde böyle delikler var bunun neden olduğunu bilen var mı nedir sebebi ?
Melis ✨ tweet mediaMelis ✨ tweet media
Türkçe
2.2K
95
4.1K
9.3M
Kadir
Kadir@kad1r·
Görüyorum insanlar son token saçmalığından sonra Claude'dan Codex gibi diğer araçlara geçiş yapıyor, Codex 10 katını veriyor diyorlar da, ben Claude'a 1 kerede anlattığım şeyi Codex'e 10 kerede anlatıyorum, mantık olarak aynı tokenı tüketmiş oluyorum günün sonunda :) (ironi)
GIF
Türkçe
0
0
0
40
Kadir
Kadir@kad1r·
Son zamanlarda claude'da şöyle bir sorun yaşayan var mı? Verdiğim iş büyük veya küçük fark etmiyor. Plan oluştur ve benden onay aldıktan sonra başla diyorum, işlemleri bitiriyor ama planı göstermiyor. Ben plan nerede hala devam ediyor musun diye sorduktan sonra gösteriyor.
Türkçe
0
0
0
26
Kadir retweetledi
Succeeded Mind
Succeeded Mind@SucceededMind·
I'm 50. If you are in your 40s, read this:
Succeeded Mind tweet media
English
42
483
2.9K
1.5M
Kadir retweetledi
Mehmet Gündoğdu
Mehmet Gündoğdu@avuntusaati·
“hiçbir şeyin sana ait olmadığı dünyada, kaybetmekten korktuğun şey nedir.” marcus aurelius
Mehmet Gündoğdu tweet media
Türkçe
7
300
2.5K
66.6K
Kadir
Kadir@kad1r·
Apple developer başvuru yaptım 2 gündür onaylanmadı. Neyimi incelediklerini çok merak ediyorum.
GIF
Türkçe
0
0
0
18