Gemma 4 120b a12b coder questions

<!-- SC_OFF --><div class="md"><p><a href="https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF">https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF</a></p> <p><a

<!-- SC_OFF --><div class="md"><p>In case you haven't heard, Google just released Multi Token Prediction drafters for Gemma 4, a speculative decoding approach that pairs the main

<!-- SC_OFF --><div class="md"><p>I'm curious about Gemma 4 12b's audio capabilities and trying to think of some use cases that the new architecture enables. Has anyone here built

<!-- SC_OFF --><div class="md"><p><a href="https://huggingface.co/z-lab/gemma-4-31B-it-DFlash">https://huggingface.co/z-lab/gemma-4-31B-it-DFlash</a></p> <p>I guess we'll have to

<!-- SC_OFF --><div class="md"><p>Hello, I've seen reviews that gemma 4 31b base is very good at roleplaying. But I can't find the gguf version of the basic gemma 4 anywhere. Only

<!-- SC_OFF --><div class="md"><p>Got inspired to try and crack this egg without using heretic.</p> <p>FP16, Q8_0 and Q4_K_M quants, plus the abliteration script for

<!-- SC_OFF --><div class="md"><p>I am running Gemma 4 31B for a project using LlamaCPP. There is no integrated main model + MTP drafter GGUF. And from what I can tell, LlamaCPP

<!-- SC_OFF --><div class="md"><p>Hi,</p> <p>has anybody succeeded in running llama.cpp with Gemma 31b dense and Gemma e4b as draft model, and simultaneously inhibit the voice