Jordi

jordivcb

2 17 108

AI & ML interests

deep learning, llm models, nlp

Recent Activity

liked a model 1 day ago

jialinyyzz/humanizer

liked a model 4 months ago

lordx64/Qwable-v1

liked a dataset 4 months ago

WithinUsAI/claude_mythos_distilled_25k

View all activity

Organizations

None yet

liked a model 1 day ago

jialinyyzz/humanizer

Text Generation • 12B • Updated 2 days ago • 33.7k • 987

liked a model 4 months ago

lordx64/Qwable-v1

Text Generation • 36B • Updated Jun 15 • 186 • 204

liked a dataset 4 months ago

WithinUsAI/claude_mythos_distilled_25k

Viewer • Updated 18 days ago • 25k • 657 • 183

upvoted a collection 4 months ago

Mellum 2

Collection

Mellum2 model weights • 6 items • Updated Jun 1 • 135

liked a model 5 months ago

Zyphra/ZAYA1-8B

9B • Updated Jun 26 • 11.4k • 595

liked a model 6 months ago

openai/privacy-filter

Token Classification • 1B • Updated Apr 22 • 336k • • 1.78k

liked a Space 6 months ago

OPF Image Anonymizer

🦀

Use OAI's Privacy Filter to redact PII info from any image

liked a dataset 6 months ago

Roman1111111/claude-sonnet-4.6-120000x

Viewer • Updated Apr 19 • 122k • 566 • 84

liked a dataset 7 months ago

nohurry/Opus-4.6-Reasoning-3000x-filtered

Viewer • Updated Mar 31 • 2.33k • 349 • 653

reacted to mitkox's post with 👍 8 months ago

Post

4922

I just pushed Claude Code Agent Swarm with 20 coding agents on my desktop GPU workstation.

With local AI, I don’t have /fast CC switch, but I have /absurdlyfast:
- 100’499 tokens/second read, yeah 100k, not a typo | 811 tok/sec generation
- KV cache: 707’200 tokens
- Hardware: 5+ year old GPUs 4xA6K gen1; It’s not the car. It’s the driver.

Qwen3 Coder Next AWQ with cache at BF16. Scores 82.1% in C# on 29-years-in-dev codebase vs Opus 4.5 at only 57.5%. When your codebase predates Stack Overflow, you don't need the biggest model; you need the one that actually remembers Windows 95.

My current bottleneck is my 27" monitor. Can't fit all 20 Theos on screen without squinting.