🎹 benchmarking models for everyone

simonko

simonko912

238 3 93

Simonko-912

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

updated a bucket 1 day ago

simonko912/my-training-scripts

published a bucket 1 day ago

simonko912/my-training-scripts

new activity 3 days ago

mradermacher/model_requests:https://huggingface.co/Blazed-Forge/Gemma-4-Sphinsikus-Chronist-V2-31B

View all activity

Organizations

updated a bucket 1 day ago

simonko912/my-training-scripts

67.3 kB

published a bucket 1 day ago

simonko912/my-training-scripts

67.3 kB

New activity in mradermacher/model_requests 3 days ago

https://huggingface.co/Blazed-Forge/Gemma-4-Sphinsikus-Chronist-V2-31B

#2866 opened 4 days ago by

KakoytoPunk

replied to appvoid's post 4 days ago

add ngram, and merge all of these together to make a frankenstein

reacted to Banaxi-Tech's post with 👀🔥🚀 4 days ago

Post

3428

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)

7 replies

replied to Banaxi-Tech's post 4 days 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)

reacted to Bc-AI's post with 🔥 4 days ago

Post

2516

Building a 6.58B sparse MoE model from scratch on a single GPU.
Hey everyone! Today is day 1 of training Smilyai-Lab's new model I call G1-MINI. It's basically the smaller version of our planned model G1 which will be 20B and activate about 2B per token. MINI activates about 1.16B params per token and is currently training right now. If no errors spring up now, I'd say i can launch sometime around September 15th~ish. Thanks to our beta testers:
@guardamarcos
@ProCreations
@juiceb0xc0de
@Timmy6767
@Sbui503
@atom77777
@Fishtiks
@smartdigitalnetworks
@EmetTheGolum
@smilyai-large-team
@MUK-IS-GOAT
@Bc-AI
@Banaxi-Tech
@vovaRL
@Datdanboi25