Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon server with no GPU
A storage appliance that shipped before AVX2 existed now runs Google's Gemma 4 26B in my basement, no GPU. Here's how we got a modern MoE model onto a CPU older than the instructions its inference…
Read the full articleYou might also wanna read
Google DeepMind's Gemma 4 12B: Encoder-free multimodal AI runs locally on 16GB VRAM
Gemma 4 12B processes text, vision, and audio natively without separate encoders, running on 16GB VRAM. For developers building local agenti
Product Hunt·1mo ago
Google's Gemma 4 12B matches larger model performance while running on standard laptops
Small enough to run locally on 16GB, the new addition to the Gemma model family with native audio support brings high performance to standar
thenewstack.io·1mo ago
Gemma Challenge: Collaborative Speed Competition to Optimize Google's Gemma-4 Model Inference
Org profile for Gemma Challenge on Hugging Face, the AI community building the future.
Use Your Mac for AI Agents: Self-Host Gemma 4 12 B with Pulumi and Tailscale
If you run AI tools and agents, you’ve probably accepted three tradeoffs: your data leaves your network, you can’t work offline, and your bi
Gemma 4: The Number Everyone's Getting Confused About
Google's Gemma 4 dropped under Apache 2.0, fully open and runs locally. But there's one mix-up worth untangling: the 31B is the quality mode
Announcing Gemma 4 on vLLM: Byte for byte, the most capable open models
How vLLM supports Google's Gemma 4 open models across NVIDIA, AMD, Intel, and TPU backends, with multimodal inputs, agentic workflows, long
Comments
Sign in to join the conversation.
No comments yet. Be the first.