mine are all <300M
well except this one but i also make under 300M https://huggingface.co/BananaMind/BananaMind-2-AI-Detect
Banaxi PRO
Banaxi-Tech
AI & ML interests
SLMs, training from scratch, LoRA, TTS, Ternary models
Recent Activity
updated a Space about 4 hours ago
Banaxi-Tech/Open_SLM_Leaderboard updated a model about 4 hours ago
Banaxi-Tech/test-mediumOrganizations
mine are all <300M
is there anything you have always wanted to achieve? that idea you know you want to be true? is possible if any
keep working 💪
achieve maximum benchmark score per param
ok
reacted to appvoid's post with 🔥 about 15 hours ago
Post
2400
if you are a tinkerer of small language models and want to stay ahead of what small models can do, follow me!!! seriously, start following people that actually still makes small models
i've made one recently btw
also, i'm keeping an eye on AxiomicLabs leaderboard, looks like the only current alternative to check where the things are going to
though, between us, i think they should add agentic/tool use benchmarks there
anyways,
enjoy!
appvoid/a-cool-model
i've made one recently btw
also, i'm keeping an eye on AxiomicLabs leaderboard, looks like the only current alternative to check where the things are going to
though, between us, i think they should add agentic/tool use benchmarks there
anyways,
enjoy!
appvoid/a-cool-model
- 18 replies
replied to kingabzpro's post about 18 hours ago
you get 0.10$ free usage then you can add usage or with HF Pro you get 2$ included usage
reacted to ManniX-ITA's post with 🚀 about 22 hours ago
Post
1872
🚀 New release: Qwen3.6-27B-A3B-Coder
A code-specialized MoE carved out of Qwen3.6-35B-A3B by pure expert pruning — no fine-tuning, no distillation. I profiled all 256 experts on balanced corpora plus targeted code benchmarks (LiveCodeBench +
MultiPL-E), built a competence map with the code classes up-weighted 1.5×, and dropped the 72 weakest experts per layer (256→184, ~35B→27B). Router, attention, norms, the MTP head and the vision tower are all
preserved; active params stay at A3B and routing is baked to top-10 (revert to top-8 anytime).
📊 Benchmarks (Q6_K, temp 0.6):
• MultiPL-E 0.840
• HumanEval 0.970
• LiveCodeBench 0.688
• GSM8K 0.970 · ARC-C 0.944 · AIME 0.733
• GPQA-Diamond 0.773 · MATH-500 0.620 · IFEval 0.730
• Average 0.808
27B footprint, A3B speed, coding that punches well above its size — and the preserved MTP head gives you speculative decoding out of the box (text + vision).
🔗 Model: ManniX-ITA/Qwen3.6-27B-A3B-Coder
📦 GGUF (+MTP): ManniX-ITA/Qwen3.6-27B-A3B-Coder-MTP-GGUF
🦙 Ollama: https://ollama.com/mannix/qwen3.6-27b-a3b-coder
A code-specialized MoE carved out of Qwen3.6-35B-A3B by pure expert pruning — no fine-tuning, no distillation. I profiled all 256 experts on balanced corpora plus targeted code benchmarks (LiveCodeBench +
MultiPL-E), built a competence map with the code classes up-weighted 1.5×, and dropped the 72 weakest experts per layer (256→184, ~35B→27B). Router, attention, norms, the MTP head and the vision tower are all
preserved; active params stay at A3B and routing is baked to top-10 (revert to top-8 anytime).
📊 Benchmarks (Q6_K, temp 0.6):
• MultiPL-E 0.840
• HumanEval 0.970
• LiveCodeBench 0.688
• GSM8K 0.970 · ARC-C 0.944 · AIME 0.733
• GPQA-Diamond 0.773 · MATH-500 0.620 · IFEval 0.730
• Average 0.808
27B footprint, A3B speed, coding that punches well above its size — and the preserved MTP head gives you speculative decoding out of the box (text + vision).
🔗 Model: ManniX-ITA/Qwen3.6-27B-A3B-Coder
📦 GGUF (+MTP): ManniX-ITA/Qwen3.6-27B-A3B-Coder-MTP-GGUF
🦙 Ollama: https://ollama.com/mannix/qwen3.6-27b-a3b-coder
- 2 replies
replied to SeaWolf-AI's post about 22 hours ago
posted an update 1 day ago
Post
71
👀 BananaMind 2 Medium is coming soon, in about 2 days.
Release Status BananaMind/BananaMind-2-Medium-Status
Release Status BananaMind/BananaMind-2-Medium-Status
reacted to their post with 🔥🧠 1 day ago
Post
2429
Introducing BananaMind 2 Nano
BananaMind 2 Nano is the smallest member of the BananaMind 2.0 family — a 10M-parameter language model that shows how much you can squeeze out of a tiny footprint. It uses the family's digit-isolated tokenizer, so it keeps solid arithmetic despite its size, and it's small enough to run just about anywhere.
Trained on 30B tokens in about a day on a single RTX 5070 Ti (16GB), 4096-token context.
Benchmarks:
Average 35.77
ARC Easy 36.20
PIQA 55.98
ARC Challenge 23.38
HellaSwag 27.50
That 35.77 average edges out Pythia-31M (~34.79) at roughly a third the parameters.
Released under Apache 2.0 on Hugging Face: BananaMind/BananaMind-2-Nano — weights, tokenizer, and config included.
BananaMind 2 Nano is the smallest member of the BananaMind 2.0 family — a 10M-parameter language model that shows how much you can squeeze out of a tiny footprint. It uses the family's digit-isolated tokenizer, so it keeps solid arithmetic despite its size, and it's small enough to run just about anywhere.
Trained on 30B tokens in about a day on a single RTX 5070 Ti (16GB), 4096-token context.
Benchmarks:
Average 35.77
ARC Easy 36.20
PIQA 55.98
ARC Challenge 23.38
HellaSwag 27.50
That 35.77 average edges out Pythia-31M (~34.79) at roughly a third the parameters.
Released under Apache 2.0 on Hugging Face: BananaMind/BananaMind-2-Nano — weights, tokenizer, and config included.
- 1 reply
reacted to wop's post with 🤗 2 days ago
Post
3502
# PixelModel v1
Last month we released PixelModel — a neural network whose weights are literally the pixels of a PNG. It was a toy: 202,752 parameters, welded to 32×32 output, trained on six solid-color swatches. It scored FID 566.84 on the Tiny-T2I-Leaderboard, mostly by producing the same yellow noise for every prompt.
Today we're releasing PixelModel v1. It is 8.5× smaller — 23,747 parameters — and it beats v0 on both benchmark metrics while being trained on 20,000 real MS-COCO caption/image pairs instead of six color swatches. The entire model now fits in a 160×149 PNG.
That image is not a visualization of the model. It is the model. All 23,747 weights, one per pixel.
## links
bench-labs
Blog post [read it here ⇗]( bench-labs/blog)
See us on the [Leaderboard ⇗]( FlameF0X/Tiny-T2I-Leaderboard)
Model card [here]( bench-labs/pixelmodel-v1)
## The catch
A 23K-parameter model does not draw sandwiches. With ~1 parameter per training image, the loss-minimizing behavior is to output the average of all plausible images for a caption — caption-conditioned color, light, and layout statistics. Food prompts come out warm and brown; sky prompts come out cool and bright. That is the ceiling for this size class, and we'd rather show it than crop around it.
# cherry on top 🍒
The model generates 600 images (cpu) in 5 (five) seconds.
Thats 5000 images in 24 seconds on cpu.
The model trained on cpu for just 30 minutes.
Last month we released PixelModel — a neural network whose weights are literally the pixels of a PNG. It was a toy: 202,752 parameters, welded to 32×32 output, trained on six solid-color swatches. It scored FID 566.84 on the Tiny-T2I-Leaderboard, mostly by producing the same yellow noise for every prompt.
Today we're releasing PixelModel v1. It is 8.5× smaller — 23,747 parameters — and it beats v0 on both benchmark metrics while being trained on 20,000 real MS-COCO caption/image pairs instead of six color swatches. The entire model now fits in a 160×149 PNG.
That image is not a visualization of the model. It is the model. All 23,747 weights, one per pixel.
## links
Blog post [read it here ⇗]( bench-labs/blog)
See us on the [Leaderboard ⇗]( FlameF0X/Tiny-T2I-Leaderboard)
Model card [here]( bench-labs/pixelmodel-v1)
## The catch
A 23K-parameter model does not draw sandwiches. With ~1 parameter per training image, the loss-minimizing behavior is to output the average of all plausible images for a caption — caption-conditioned color, light, and layout statistics. Food prompts come out warm and brown; sky prompts come out cool and bright. That is the ceiling for this size class, and we'd rather show it than crop around it.
# cherry on top 🍒
The model generates 600 images (cpu) in 5 (five) seconds.
Thats 5000 images in 24 seconds on cpu.
The model trained on cpu for just 30 minutes.
replied to ProCreations's post 2 days ago
grug 27b always better than 35b a3b
posted an update 3 days ago
Post
2429
Introducing BananaMind 2 Nano
BananaMind 2 Nano is the smallest member of the BananaMind 2.0 family — a 10M-parameter language model that shows how much you can squeeze out of a tiny footprint. It uses the family's digit-isolated tokenizer, so it keeps solid arithmetic despite its size, and it's small enough to run just about anywhere.
Trained on 30B tokens in about a day on a single RTX 5070 Ti (16GB), 4096-token context.
Benchmarks:
Average 35.77
ARC Easy 36.20
PIQA 55.98
ARC Challenge 23.38
HellaSwag 27.50
That 35.77 average edges out Pythia-31M (~34.79) at roughly a third the parameters.
Released under Apache 2.0 on Hugging Face: BananaMind/BananaMind-2-Nano — weights, tokenizer, and config included.
BananaMind 2 Nano is the smallest member of the BananaMind 2.0 family — a 10M-parameter language model that shows how much you can squeeze out of a tiny footprint. It uses the family's digit-isolated tokenizer, so it keeps solid arithmetic despite its size, and it's small enough to run just about anywhere.
Trained on 30B tokens in about a day on a single RTX 5070 Ti (16GB), 4096-token context.
Benchmarks:
Average 35.77
ARC Easy 36.20
PIQA 55.98
ARC Challenge 23.38
HellaSwag 27.50
That 35.77 average edges out Pythia-31M (~34.79) at roughly a third the parameters.
Released under Apache 2.0 on Hugging Face: BananaMind/BananaMind-2-Nano — weights, tokenizer, and config included.
- 1 reply
posted an update 4 days ago
Post
134
We're excited to release BananaMind 2 MoE, a new addition to the BananaMind 2 series!
BananaMind 2 MoE is a sparse mixture-of-experts model with 25M total parameters but only 2M active per token, Like the rest of the series, it uses our custom digit-aware BPE tokenizer that keeps every digit isolated, fixing the core arithmetic weakness of our earlier models. It's trained on 30B tokens from FineWeb-Edu, DCLM, Cosmopedia-v2 and FineMath-4+, and outperforms Pythia-31M on average despite activating just 2M parameters.
Check it out at
BananaMind/BananaMind-2-MoE
BananaMind 2 Nano is Coming Next. Already training. Apache 2.0.
BananaMind 2 MoE is a sparse mixture-of-experts model with 25M total parameters but only 2M active per token, Like the rest of the series, it uses our custom digit-aware BPE tokenizer that keeps every digit isolated, fixing the core arithmetic weakness of our earlier models. It's trained on 30B tokens from FineWeb-Edu, DCLM, Cosmopedia-v2 and FineMath-4+, and outperforms Pythia-31M on average despite activating just 2M parameters.
Check it out at
BananaMind/BananaMind-2-MoE
BananaMind 2 Nano is Coming Next. Already training. Apache 2.0.
reacted to ProCreations's post with 🤝 4 days ago
Post
3153
sad grug news:
I have burnt a lot of GPU credits already just making grug and it’s variants (I do not own a workstation yet) and grug 35b has a pretty bad issue but if I continue burning GPU credits to fix it then it will take even longer to get the workstation I am working for… so the fix may take a few days or never happen.
The error:
I tested it in opencode after benchmarks were good and after release (my mistake) and it had pretty bad repetition failure and simply didn’t work. so.. yea.
I have burnt a lot of GPU credits already just making grug and it’s variants (I do not own a workstation yet) and grug 35b has a pretty bad issue but if I continue burning GPU credits to fix it then it will take even longer to get the workstation I am working for… so the fix may take a few days or never happen.
The error:
I tested it in opencode after benchmarks were good and after release (my mistake) and it had pretty bad repetition failure and simply didn’t work. so.. yea.
- 4 replies
reacted to their post with 👍 4 days ago
Post
3781
We are announcing 3 more models in our BananaMind 2 Family of models!
BananaMind 2 Nano, a small 10M parameter model, fits on your Pentium 4
BananaMind 2 Medium, our medium model, 50M parameters
BananaMind 2 MoE, 25M parameters, 2M active per tokens as fast as a 2M.
Because of this our release dates have changed a bit our currently estimates are:
BananaMind 2 MoE July 16-18
BananaMind 2 Nano July 18-20
BananaMind 2 Medium July 24-28
BananaMind 2 Pro August 10-16
Keep in mind these dates are estimates and we don't have a speed number currently, we will post for details going forward!
BananaMind 2 Nano, a small 10M parameter model, fits on your Pentium 4
BananaMind 2 Medium, our medium model, 50M parameters
BananaMind 2 MoE, 25M parameters, 2M active per tokens as fast as a 2M.
Because of this our release dates have changed a bit our currently estimates are:
BananaMind 2 MoE July 16-18
BananaMind 2 Nano July 18-20
BananaMind 2 Medium July 24-28
BananaMind 2 Pro August 10-16
Keep in mind these dates are estimates and we don't have a speed number currently, we will post for details going forward!
reacted to Hari5115's post with 👍 5 days ago
Post
207
Fair warning space/photograhy lovers: this is weirdly addictive, Just one date becomes thirty !
There's a spot on the internet that shows you the exact image nasa shared with the world on any day since 1995. Type your birthday and see what the universe was up to.
(Born before 1995? Ah — the cosmos wasn't posting yet. You're officially more vintage than the dataset. 😎 Try a big life date instead.) 😅
🔭 See yours → Hari5115/cosmic-moment
Or hit Surprise me and let the universe pick.
Post the image you got below 👇 — let's see whose day space showed off for. 🌠
Built on the open nasa apod dataset · public domain · not affiliated with nasa
Dataset: 📦 Hari5115/nasa-apod
#space #photography #astro #cosmic
There's a spot on the internet that shows you the exact image nasa shared with the world on any day since 1995. Type your birthday and see what the universe was up to.
(Born before 1995? Ah — the cosmos wasn't posting yet. You're officially more vintage than the dataset. 😎 Try a big life date instead.) 😅
🔭 See yours → Hari5115/cosmic-moment
Or hit Surprise me and let the universe pick.
Post the image you got below 👇 — let's see whose day space showed off for. 🌠
Built on the open nasa apod dataset · public domain · not affiliated with nasa
Dataset: 📦 Hari5115/nasa-apod
#space #photography #astro #cosmic
posted an update 6 days ago
Post
3781
We are announcing 3 more models in our BananaMind 2 Family of models!
BananaMind 2 Nano, a small 10M parameter model, fits on your Pentium 4
BananaMind 2 Medium, our medium model, 50M parameters
BananaMind 2 MoE, 25M parameters, 2M active per tokens as fast as a 2M.
Because of this our release dates have changed a bit our currently estimates are:
BananaMind 2 MoE July 16-18
BananaMind 2 Nano July 18-20
BananaMind 2 Medium July 24-28
BananaMind 2 Pro August 10-16
Keep in mind these dates are estimates and we don't have a speed number currently, we will post for details going forward!
BananaMind 2 Nano, a small 10M parameter model, fits on your Pentium 4
BananaMind 2 Medium, our medium model, 50M parameters
BananaMind 2 MoE, 25M parameters, 2M active per tokens as fast as a 2M.
Because of this our release dates have changed a bit our currently estimates are:
BananaMind 2 MoE July 16-18
BananaMind 2 Nano July 18-20
BananaMind 2 Medium July 24-28
BananaMind 2 Pro August 10-16
Keep in mind these dates are estimates and we don't have a speed number currently, we will post for details going forward!
replied to ProCreations's post 6 days ago
grug 27b would be nice