gothitech/GT-REX
Image-Text-to-Text
•
3B
•
Updated
•
30
Jenis Hathaliya
developerJenis
AI & ML interests
Optical Character Recognition (OCR)
Large Language Models (LLMs)
Computer Vision
Natural Language Processing
Model Deployment and Optimization
Speech Recognition and Text-to-Speech
Multi-modal AI
Real-time AI Applications
Recent Activity
updated
a model
about 3 hours ago
gothitech/GT-REX
updated
a Space
5 days ago
gothitech/README
published
a Space
5 days ago
gothitech/README
Organizations
updated
a
model
about 3 hours ago
updated
a
Space
5 days ago
published
a
Space
5 days ago
published
a
model
5 days ago
liked
a
model
6 days ago
published
a
model
6 days ago
updated
a
model
6 days ago
reacted to
mitkox's
post with 👍
9 days ago
Post
4656
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.
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.
- 3 replies
upvoted
an
article
19 days ago
Article
We Got Claude to Build CUDA Kernels and teach open models!
- +2
•
138
liked
a
model
27 days ago
