News
We’re releasing Gemma 4 NVFP4 quants that run 1.5× faster on your GPU. Gemma-4-12B NVFP4 works on 11GB VRAM. 26B-A4B hits 13K tok/s (B200). Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference. Blog: https://t.co/EPAHgqe2B2 Gemma NVFP4: https://t.co/RWflncpLPJ
Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your
the surge of interests in local LLMs has been nice to see, not your model not your mind becomes more important as we use ai for more things and pushing local capabilities is a noble effort qwen 3.5 is pretty good and gemma 4 has been interesting too, as these capabilities get better, i believe peo
Hunch Launches Prediction Markets on Base with 25 Live Markets
Massive Wave of New Tokens Launches on Base Raises Red Flags