@grok@VaibhavSisinty@grok so basically another idiot claiming some "truths" based on farts from his ass.. demanding regulation of opensource at the end..?
Today we are introducing Escha-W2 quantization.
A 2-bit Qwen3.6-35B-A3B model built for fast, local inference. The complete model is 12.3GB on disk—small, enough to run on a single consumer GPU — while averaging ~100% of FP8 performance across 12 benchmarks, including:
MMLU-Pro: 80.9
MATH-500: 93.8
GPQA-Diamond: 77.8
LiveCodeBench v6: 62.6
BFCL tool use: 88.9
RULER 8K–128K: 89.9
Commonsense-6: 76.1
On a single RTX 4090, the model runs:
225 tok/s single-stream generation
on 12.3GB on-disk model size
Compressing a 35B MoE model this far without collapsing its capabilities required more than a standard quantization pass.
We built an end-to-end compression system combining state-of-the-art low-bit quantization with model-aware fine tuning and recovery to preserve capabilities most vulnerable to low-bit error.
Quantizing the Qwen 3.6 35B model - from the base model to the final deployable checkpoint — took approximately 10 hours to complete.
Escha-W2 runs through a custom Qwen3-MoE runtime, which includes the weight loader, low-bit decoding kernels and serving integration required to execute the Escha format efficiently. The runtime currently supports SGLang and ZML deployment. vLLM and llama.cpp will be supported in the next release.
No retraining from scratch. No specialized accelerator. One consumer GPU.
Model download: https://t.co/hbO3VuoDGU
Runtime download: https://t.co/hrTpO4FvuA
Apache-2.0 model and runtime.
🚨🔥 Elon Musk just ENDED this snobby British reporter's career !
Question "we started this conversation saying superlatives. It's why people loathe you. Do you understand that?"
Musk "I don't care, but the fact that, as you pointed out, a quarter billion people follow me is that I think a lot more people actually like me than don't.
And I think a lot more people hate you and the media more than you realize"
🚨 BREAKING: After President Trump applied pressure on the Saudi Crown Prince to increase his U.S. investment to $1 TRILLION, the Crown Prince agreed ON THE SPOT
THIS is the Art of the Deal in action
SAUDI CROWN PRINCE: “Mr. President, we are going to increase that $600 billion to almost $1 trillion. In technology, Al, magnets, that will create a lot of investment opportunities…”
TRUMP: “You're saying to me now the $600 billion will be $1 trillion?”
SAUDI CROWN PRINCE: “Definitely!”
Incredible.
🚨BREAKING NEWS
Polish President Karol Nawrocki:
Ukraine is an ungrateful and rogue country. The mentality that collaborated with the Nazis and massacred our people in Volhynia is now back in Ukraine.