11:00
Gemma 4’s Big Update in 4-Bit QAT — Low VRAM, Local
Fahd Mirza covers the most significant update to Google's Gemma 4 model to date: 11 targeted fixes spanning tool calling, chat format...
Sort by: Newest Items
There are 5 items in this page
11:07
NVIDIA Puzzle 75B: A 120B Model Squeezed onto ONE GPU
NVIDIA's Nemotron Lab 3 Puzzle 75B compresses the 120B-parameter Nemotron Super model down to 75B total parameters — with only 9.3B a...
09:52
Run DeepSeek DSpark on Qwen3 Locally and Reproduce the Speedup
Fahd Mirza walks through a complete hands-on reproduction of DeepSeek's DeepSpark speculative decoding results on a single NVIDIA RTX...
16:47
Google QAT vs Unsloth QAT + MTP – Which Gemma 4 12B Is Actually Better?
This video pits two quantized versions of Google's Gemma 4 12B against each other in a practical, locally-run benchmark: Google's own...
13:08
Gemma 4 12B QAT + MTP on llama.cpp Locally – Twice the Speed, Same Quality?
This video by Fahd Mirza walks through running Google's newly released Gemma 4 12B QAT (Quantization-Aware Training) model alongside...