Huggy
🐶
456
Play with an AI dog that catches sticks you throw
🎹 benchmarking models for everyone
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
queueing models for mradermacher
contact:
dc: simonko_11015
github: Simonko-912
Recent Activity
liked a Space 5 days ago
ThomasSimonini/Huggy updated a model 5 days ago
simonko912/simbot-4m published a model 5 days ago
simonko912/simbot-4mOrganizations
liked a
Space 5 days ago
updated a
model 5 days ago
published a
model 5 days ago
replied to Banaxi-Tech's post 6 days ago
you can use it BUT mention it was trained with it please
okay, and also i modified it for me to support intel gpus, and be a site i can reach instead of electron app, so i would like that to be built in (to be able to host as web site or electron) and that intel gpu thing, but for now the hardly working version what i made with opencode is enough
replied to Banaxi-Tech's post 6 days ago
yeah these will surely beat my models, maybe ill try it to see lol
Is it really 19B?
1
#1 opened 9 days ago
by 
Orogamy
updated a
model 9 days ago
published a
model 9 days ago
Model settings question and what we tried, what worked and what didn't.
1
#1 opened 13 days ago
by 
oneletterz
Interdependent Infrastructure Failure Analysis 2039
601
#9 opened 9 months ago
by 
mradermacher
Please add the following outstanding translation models from Cohere For AI
4
#2912 opened 20 days ago
by 
Abu-Dju
✴️ Spark-X2.5
10
#2887 opened 27 days ago
by 
redaihf
updated a
bucket about 1 month ago
published a
bucket about 1 month ago
https://huggingface.co/Blazed-Forge/Gemma-4-Sphinsikus-Chronist-V2-31B
1
#2866 opened about 1 month ago
by 
KakoytoPunk
add ngram, and merge all of these together to make a frankenstein
reacted to Banaxi-Tech's post with 👀🔥🚀 about 1 month ago
Post
3459
Introducing BananaMindOS 3.0
- Complete modern UI redesign
- Adds support for Qwen3.5 0.8B, LFM2.5 230M,350M, SmolLM2 360M, Gemma 3 270M.
- Adds Q7,Q6,Q5,Q3,Q1 quantization formats with a easy to use precision slider
- And more!
The new UI includes:
- New 1024×768 High Quality interface.
- Photographic QOI background.
- Transparent BananaMind, CPU, cube, mouse, and Send icons.
- Proper bitmap cursor.
- Rounded translucent panels and cards.
- Modern model-loading progress window.
- Redesigned inference screen with response and prompt panels.
- Localized redraws for the cursor, clicks, loading progress, and precision slider.
Notice: Qwen3.5 0.8B currently generates garbled text, it will be fixed tomorrow.
See it for yourself
Now Available at https://github.com/BananaMind/BananaMindOS
Prebuild ISOs coming soon!
(also press ? + G if you want to load try to load a 6MB RAM model on 5MB may break)
- Complete modern UI redesign
- Adds support for Qwen3.5 0.8B, LFM2.5 230M,350M, SmolLM2 360M, Gemma 3 270M.
- Adds Q7,Q6,Q5,Q3,Q1 quantization formats with a easy to use precision slider
- And more!
The new UI includes:
- New 1024×768 High Quality interface.
- Photographic QOI background.
- Transparent BananaMind, CPU, cube, mouse, and Send icons.
- Proper bitmap cursor.
- Rounded translucent panels and cards.
- Modern model-loading progress window.
- Redesigned inference screen with response and prompt panels.
- Localized redraws for the cursor, clicks, loading progress, and precision slider.
Notice: Qwen3.5 0.8B currently generates garbled text, it will be fixed tomorrow.
See it for yourself
Now Available at https://github.com/BananaMind/BananaMindOS
Prebuild ISOs coming soon!
(also press ? + G if you want to load try to load a 6MB RAM model on 5MB may break)
- 7 replies
replied to Banaxi-Tech's post about 1 month ago
Im making a iso of all the listed models on github, q6, q8, q4 and the extra 16 and 32 bit. Excited for my multitool usb.
also made a suggdestion on github to add support for small diffusion models (could work on 2000's pcs)