SLiNeP Demo
🐢
1
Demo of the small SLiNeP ai model, it's made to be finetuned
simonko
simonko912
·
AI & ML interests
guy with low end hardware learning about llm's and learning about finetuning
my hardware:
intel xeon E5v4
32gb ddr4 ram
amd rx 5700 8gb vram (Hf allows to set from 6600 lol)
512gb ssd
contact:
dc: simonko_11015
github: Simonko912
Recent Activity
new activity
about 4 hours ago
mradermacher/model_requests:My first English model
liked
a Space
about 5 hours ago
simonko912/SLiNeP-demo
updated
a Space
about 6 hours ago
simonko912/SLiNeP-demo
Organizations
None yet
My first English model
8
#1805 opened about 14 hours ago
by
simonko912
liked
a
Space
about 5 hours ago
updated
a
Space
about 6 hours ago
published
a
Space
about 6 hours ago
liked
2
models
about 6 hours ago
reacted to
melvindave's
post with 🚀🔥
about 9 hours ago
Post
1306
I made my own avatar banner maker
https://avatar.donvitocodes.com/
Using Claude Code and Opus 4.6 in a day
I use it in my HF profile too
https://avatar.donvitocodes.com/
Using Claude Code and Opus 4.6 in a day
I use it in my HF profile too
The Rise of the Machines: Why We Should Celebrate Our Replacement by AI
🔥
👍
1
300
#7 opened 5 months ago
by
mradermacher
reacted to
mitkox's
post with 👍
about 12 hours ago
Post
2585
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.
- 1 reply
updated
2
models
about 14 hours ago
liked
a
model
about 22 hours ago
liked
a
dataset
about 22 hours ago
liked
3
models
1 day ago
published
a
model
1 day ago
liked
a
dataset
1 day ago
updated
a
dataset
1 day ago