Diana Park
Contributor profile at Tidqom · Singapore · 12 articles
Crypto and Web3 correspondent following token markets, DeFi, and regulation. Former financial analyst.
@dianaparkweb3 on XLatest articles by Diana Park
- guides
Ollama Answers Get Cut Off Mid-Sentence: num_ctx vs num_predict Explained
Truncated replies and models that "forget" the start of a long document come from two different settings. Here is how I tell them apart and the values I use.
8/1/2026 · 5 min read - guides
Ollama Error "model requires more system memory": How I Fixed It in 10 Minutes
Ollama refuses to load a model and says it needs more system memory than you have. Here is exactly what the number means and the four fixes that worked on my 32 GB / RTX 3060 box.
8/1/2026 · 6 min read - ai-models
DeepSeek-R1 Repeats Itself or Outputs Gibberish: The 4 Settings That Fixed It
Endless loops, repeated sentences or mojibake from DeepSeek-R1 are almost always sampling or quantization — not a broken model. The exact parameters I now use.
8/1/2026 · 6 min read - guides
Ollama Filled My Disk: How I Moved the Models Directory Safely
Ollama stores every model on the system drive by default. The exact steps I used to move ~/.ollama/models to a second drive on Linux, Windows and macOS without re-downloading.
8/1/2026 · 5 min read - guides
Ollama Not Using My NVIDIA GPU in WSL2: The Fix That Finally Worked
Ollama says "no compatible GPUs were discovered" inside WSL2 even though nvidia-smi works. Here is the exact driver, toolkit and verification sequence that fixed it on my RTX 3060.
8/1/2026 · 6 min read - guides
Ollama Pull Fails with "max retries exceeded" or EOF: How I Get Downloads to Finish
Model downloads that stall at 97% or die with EOF. The five things that fixed it for me: resume behaviour, MTU, DNS, proxy variables and a corrupted blob cache.
8/1/2026 · 5 min read - guides
Ollama "connection refused on 127.0.0.1:11434": The 5 Causes I Have Actually Hit
Your client cannot reach Ollama on port 11434. Here are the five real causes — service not running, wrong host binding, WSL networking, port conflict, and Docker — with the command that fixes each.
8/1/2026 · 6 min read - ai-models
DeepSeek-R1 Shows Its <think> Tags in the Output — Here Is How I Strip Them
DeepSeek-R1 prints its whole reasoning chain before the answer. Three ways I remove it: prompt-level, API-level parsing, and a small wrapper I use in every script.
8/1/2026 · 5 min read - guides
كيف شغّلت نموذج ذكاء اصطناعي على لابتوب بدون كرت شاشة (تجربتي الكاملة 2026)
معالج i5 و16 جيجا رام وبدون كرت شاشة منفصل: 9 كلمات في الثانية على نموذج 7B. الإعدادات التي غيّرت النتيجة والأخطاء التي أهدرت وقتي.
7/30/2026 · 6 min read - guides
Ollama Running Slow? 7 Fixes That Actually Worked on My Machine
Same laptop, same 7B model: 4 tokens/s before, 31 after. Seven settings were wrong. Here is the exact order I check them in.
7/30/2026 · 7 min read - guides
Transcribing Audio Locally with Whisper: My Actual Workflow (No Uploads)
Two hours of interview audio transcribed on a laptop in eleven minutes, offline. The model size that is worth it, the flags that matter, and how I handle speaker names.
7/29/2026 · 4 min read 
CryptoBitcoin to $200K? Wall Street Analysts Are Suddenly Bullish Again
After the latest halving and spot ETF inflows, top analysts at JPMorgan and Standard Chartered are calling for new all-time highs by year-end.
7/13/2026 · 6 min read