We're announcing Klein SL Pro, our new model at Klein ML. It's doing post-training of Qwen3.8 Flash Next to make IT fit on 16GB VRAM.
It works by converting its MoE to SLMoE, SLMoE is an architecture, that chooses experts per response, not per token anymore.
This makes it so you can offload everything else to the disk and not get slow speed.
We're also seeking more compute to do this same thing on Deepseek V4.1 Flash, allowing it to run on 16GB VRAM tightly and definitely on 24GB. If you have hardware, more than 200B of VRAM in total, create a discussion klein-ml/README.
We've did some updates to Banaxi-Tech/TTS-Arena and now, everyone who uses the TTS Arena alot will get featured in our Klein TTS Release. Using it REALLY helps us alot so please use it.
Updates on the sizes: Klein TTS Flash Lite with 0.4M parameters, Klein TTS Flash with 1.7M parameters, Klein TTS Pro with 13M parameters and Ultra with 21M.
BananaMind 3 is going to be an comeback. Sorry for the BGA things ( i genuinely didnt know about nsa existing and yes I used aiiii) Were going to use our BananaMind 2.1 Unified architecture with some changes + NSA and some other stuff.
saicr have found a very interesting "thing" we call ADN via interpretabillity. It appears on EVERY prompt sent to the model. More on that later. Also I made a X account follow it for more updates: @banaxitech
klein-ml have finished stage 1 of KV1 1.2B, we don't think we will need additional stages.
KV1 2.6B is near the midpoint of training, going well so far, its going to be our most agentic model yet.
We have released Klein Code Bench klein-ml/klein-code-bench, a benchmark testing whether models can build complete projects from scratch. It contains a easy, intermediate, hard and max subset.
Here are some benchmarks of the current KV1 1.2B
It retains 75.8% of FP16 intelligence.
We are also announcing that we at
klein-ml are working on Klein 24B A2B which will be our first model featuring ternary weight quantization.
We're going to take some models, do a bit of continued training on them and QAT them for only a 2 bit KV cache. And because of what happened with BGA, and this is also kind of some research stuff, here's what we're going to change: We're going to always, before we release how and make any claims, release our results. We also would like (idk if we can) to have some external reviewers before releasing them, I'M talking to YOU @AtAndDev and @mithulaartigala And we're going to properly cite other research.
The models we are going to release is: KV1 1.2B, based on LFM 2.5 1.2B Instruct KV1 2.6B, based on LFM 2.5 2.6B Instruct KV1 4B, based on Qwen3.5 4B.
If we get enough compute, we may also train: KV1 9B
And if you guys want to a ~27B model, you guys decide which, either on LFM 2.5 24B A2B, Qwen3.8 27B, or Qwen3.6 35B A3B.
Our goal is to get 2 bit, at 4 bit quality.
Here's an image of our current progress, KV1 is at 3 bit, not 4 bit, but it will improve!
And we're releasing something major again now, if you have seen Grok Bot, its very powerful, but there isn't really a local alternative yet.
Today we're releasing Minds, they're personal AI bots that live on your computer. They can run anywhere, on your phone, on your mac, on windows, and even on linux.
They support OpenAI Oauth as the main integration because most people already have a ChatGPT sub.
But locally, It supports ANY openai compatible api which allows you to setup ollama and llama.cpp and everything else.
It uses Jev for command approval on OpenRouter and Muse Spark Transcribe for transcription.
1. Should I release all Pebble 1.5 models together in one big launch, or release each model individually as it's ready? 2. What would you like to see from the Pebble models? Any specific features, capabilities, or improvements? 3. What would you like to see from basically AI as a company in general?
We are now announcing BananaMind 3 🍌! (not ai for those emoji guys)
All models will use BGA (which is almost just NSA) and our BM3X architecture. Its sizes will be: BananaMind 3 Flash Lite, 3M parameters at a context of 8K context. BananaMind 3 Lite, 10M parameters with 16K context. BananaMind 3 Flash, 25M Parameters with 16K context. BananaMind 3 Pro, 50M parameters with 24K context. BananaMind 3 Ultra, 100M parameters with 32K context. And lastly, BananaMind 3 Max with 150M parameters and 64K CONTEXT.
I can assure you BananaMind 3 Max WILL beat GPT X3 or match it, we won't release it otherwise. We hope for a 40+ INTELLIGENCE INDEX!
BananaMind 3 may also be partnered with dot labs.
We will cancel BananaMind 2.1 and BananaMind 2 Ultra.
As of the BETU SLM Leaderboard we may need to release it after October 11, im very busy right now (even though we said We will release BETU leaderboard before Oct 11 😟)
We have released BGA! And wow, It provides 256x (and 512x at the end of 1M) yes 256x LESS attention compute at 1M context window. That means you can train a 1M context window at the compute of a ~4K context window.
