I m hyped up to my neck -
Upcoming weeks
We have Mass release of models
- BananaMind 2 Pro
-Gpt X 2.5
-BanaMind 3 series with TX4
-Qyrou models
-Supra Labs modelsMany more
Bananamind 2 still, not 3
But on August 3!
Banaxi PRO
Banaxi-Tech
AI & ML interests
SLMs, training from scratch, LoRA, TTS, Ternary models. Contact at banaxitech@gmail.com
Recent Activity
new activity 6 minutes ago
AxiomicLabs/Open_SLM_Leaderboard:New model repliedto their post 9 minutes ago
We're announcing BananaMind 2 Micro, our smallest model in the BananaMind 2 model family.
This model is not released yet, training has not started yet.
It uses only 2.9M parameters, while being overtrained on 75B tokens to get the maximum intelligence per parameter.
The key changes are:
No more AdamW, the model will use the Muon optimizer offering up to 2x faster convergence and higher lr.
LR goes to 2.2e-2.
We're adding the XSA refresh gate from the TX4 architecture into our own.
Training will start on August 3, release date is estimated to be August 4-6.
On August 3 we will also release our Public Preview of BananaMind 2 Pro.
Follow us to know when our models release
https://huggingface.co/BananaMind
@Banaxi-Tech
repliedto their post 10 minutes ago
We're announcing BananaMind 2 Micro, our smallest model in the BananaMind 2 model family.
This model is not released yet, training has not started yet.
It uses only 2.9M parameters, while being overtrained on 75B tokens to get the maximum intelligence per parameter.
The key changes are:
No more AdamW, the model will use the Muon optimizer offering up to 2x faster convergence and higher lr.
LR goes to 2.2e-2.
We're adding the XSA refresh gate from the TX4 architecture into our own.
Training will start on August 3, release date is estimated to be August 4-6.
On August 3 we will also release our Public Preview of BananaMind 2 Pro.
Follow us to know when our models release
https://huggingface.co/BananaMind
@Banaxi-Tech
Organizations
New model
16
#63 opened 4 days ago
by 
simonko912
replied to their post 9 minutes ago
replied to their post 10 minutes ago
I m hyped up to my neck -
Upcoming weeks
We have Mass release of models
- BananaMind 2 Pro
-Gpt X 2.5
-BanaMind 3 series with TX4
-Qyrou models
-Supra Labs modelsMany more
Bananamind 2 still, not 3
reacted to LH-Tech-AI's post with 🔥🤗 about 2 hours ago
Post
113
Announcing The Supra2 Family And Supra2-100M
Today, we are announcing a brand-new series of SupraLabs models: Supra2
This series will feature various models, including such as:
- 🐜 Supra2-Nano (0.4M) → The smallest Supra2 model.
- 🤏 Supra2-Small (1.4M) → The tiny model that runs everywhere.
- 💪 Supra2-Medium (25M) → Our medium class model in the Supra2 family. The powerful midsizer.
- 🔥 Supra2-Pro (100M): base, instruct, reasoning, code, math and more! → The most capable model yet! A real allrounder for all your everyday tasks.
- 🎨 Supra2-IMG → our generative text-to-image model
...and many more...
Current progress:
- Nano (0.4M) and Small (1.4M): in training; almost done. Baseline set.
- Medium (25M): coming soon...
- Pro (100M): in training; finishes in 66 hours - Monday, 3rd August 2026, 12:00AM
- IMG: coming soon...
You can support us with a like and follow if you want!
Don't miss our next release! Stay tuned...
Today, we are announcing a brand-new series of SupraLabs models: Supra2
This series will feature various models, including such as:
- 🐜 Supra2-Nano (0.4M) → The smallest Supra2 model.
- 🤏 Supra2-Small (1.4M) → The tiny model that runs everywhere.
- 💪 Supra2-Medium (25M) → Our medium class model in the Supra2 family. The powerful midsizer.
- 🔥 Supra2-Pro (100M): base, instruct, reasoning, code, math and more! → The most capable model yet! A real allrounder for all your everyday tasks.
- 🎨 Supra2-IMG → our generative text-to-image model
...and many more...
Current progress:
- Nano (0.4M) and Small (1.4M): in training; almost done. Baseline set.
- Medium (25M): coming soon...
- Pro (100M): in training; finishes in 66 hours - Monday, 3rd August 2026, 12:00AM
- IMG: coming soon...
You can support us with a like and follow if you want!
Don't miss our next release! Stay tuned...
- 1 reply
replied to danielhanchen's post about 14 hours ago
0.5 or 1tps
liked a
model 1 day ago
replied to their post 1 day ago
The chart has a 805 line?
upvoted an article 1 day ago
Article
Training a 2.7B MoE from scratch for $200, one GPU at a time
vovaRL
• • 3 updated a
dataset 1 day ago
liked a
model 1 day ago
What
2
#3 opened 1 day ago
by Banaxi-Tech
liked a
model 1 day ago
reacted to their post with 😎🔥🤗 1 day ago
Post
2193
We're announcing BananaMind 2 Micro, our smallest model in the BananaMind 2 model family.
This model is not released yet, training has not started yet.
It uses only 2.9M parameters, while being overtrained on 75B tokens to get the maximum intelligence per parameter.
The key changes are:
No more AdamW, the model will use the Muon optimizer offering up to 2x faster convergence and higher lr.
LR goes to 2.2e-2.
We're adding the XSA refresh gate from the TX4 architecture into our own.
Training will start on August 3, release date is estimated to be August 4-6.
On August 3 we will also release our Public Preview of BananaMind 2 Pro.
Follow us to know when our models release
BananaMind
@Banaxi-Tech
This model is not released yet, training has not started yet.
It uses only 2.9M parameters, while being overtrained on 75B tokens to get the maximum intelligence per parameter.
The key changes are:
No more AdamW, the model will use the Muon optimizer offering up to 2x faster convergence and higher lr.
LR goes to 2.2e-2.
We're adding the XSA refresh gate from the TX4 architecture into our own.
Training will start on August 3, release date is estimated to be August 4-6.
On August 3 we will also release our Public Preview of BananaMind 2 Pro.
Follow us to know when our models release
@Banaxi-Tech
- 9 replies
posted an update 1 day ago
Post
2193
We're announcing BananaMind 2 Micro, our smallest model in the BananaMind 2 model family.
This model is not released yet, training has not started yet.
It uses only 2.9M parameters, while being overtrained on 75B tokens to get the maximum intelligence per parameter.
The key changes are:
No more AdamW, the model will use the Muon optimizer offering up to 2x faster convergence and higher lr.
LR goes to 2.2e-2.
We're adding the XSA refresh gate from the TX4 architecture into our own.
Training will start on August 3, release date is estimated to be August 4-6.
On August 3 we will also release our Public Preview of BananaMind 2 Pro.
Follow us to know when our models release
BananaMind
@Banaxi-Tech
This model is not released yet, training has not started yet.
It uses only 2.9M parameters, while being overtrained on 75B tokens to get the maximum intelligence per parameter.
The key changes are:
No more AdamW, the model will use the Muon optimizer offering up to 2x faster convergence and higher lr.
LR goes to 2.2e-2.
We're adding the XSA refresh gate from the TX4 architecture into our own.
Training will start on August 3, release date is estimated to be August 4-6.
On August 3 we will also release our Public Preview of BananaMind 2 Pro.
Follow us to know when our models release
@Banaxi-Tech
- 9 replies
reacted to danielhanchen's post with ❤️ 2 days ago
Post
3502
Kimi K3 can now be run locally! ✨
The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).
Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.
GGUF: unsloth/Kimi-K3-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k3
The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size).
Run on a Mac Studio connected with 128GB RAM device. Kimi K3 is the strongest open model to date.
GGUF: unsloth/Kimi-K3-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k3
- 5 replies
reacted to Enderchef's post with 🔥 2 days ago
Post
4311
Introducing GCI-Bench, Glint Research's first benchmark!
This 5000-question bench benchmarks attention and gradients; it gives a prompt and unrelated filler parts. The goal is to benchmark if the model understands and attends to the important parts more than the unimportant parts.
I've already benchmarked on the top 5 models on our Leaderboard(Glint2, Supra 50M, Glint1.3, GPT S 5M, GPT X2 125M)
Pending benchmark status at OpenEvals/README#2
Glint-Research/GCI_Bench
This 5000-question bench benchmarks attention and gradients; it gives a prompt and unrelated filler parts. The goal is to benchmark if the model understands and attends to the important parts more than the unimportant parts.
I've already benchmarked on the top 5 models on our Leaderboard(Glint2, Supra 50M, Glint1.3, GPT S 5M, GPT X2 125M)
Pending benchmark status at OpenEvals/README#2
Glint-Research/GCI_Bench
- 6 replies
updated a
Space 2 days ago