APIUp to 25% cheaper than official pricesTry the API →
Hermes
APIModelsCases
Back to News
modelLlmsGpus

Google DeepMind Shrinks Gemma 4 E4B to 5GB Without Losing Reasoning Power

Google released quantization-aware trained Q4_0 GGUF checkpoints of Gemma 4 E4B, delivering near-bfloat16 quality in a 5.15 GB on-device package.

Google DeepMind Shrinks Gemma 4 E4B to 5GB Without Losing Reasoning Power
Source
Google
Published
Author
AlphaSignal Newsroom
Read
1 min read

Google released quantization-aware trained Q4_0 GGUF checkpoints of Gemma 4 E4B, delivering near-bfloat16 quality in a 5.15 GB on-device package.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

UkisAI Squeezes Swift 1.5's 27B Reasoning Model Into 8.42GB for Consumer GPUs
AlphaSignal · model

UkisAI Squeezes Swift 1.5's 27B Reasoning Model Into 8.42GB for Consumer GPUs

Bartowski Packs Qwen2.5-32B Into a 9GB File for Local Machines
AlphaSignal · model

Bartowski Packs Qwen2.5-32B Into a 9GB File for Local Machines

Atomic Chat Runs a 177B Qwen3.8-Flash-Next on a 64 GB Mac
AlphaSignal · model

Atomic Chat Runs a 177B Qwen3.8-Flash-Next on a 64 GB Mac