Gemma 4 12B

On the same machine, the author compared three Gemma variants on 76 synthetic cases: Gemma 4 E4B reached 97%, Gemma 3 4B reached 78% with 5 false positives, and Gemma 4 12B reached 80% with 32 call timeouts.

Google Gemma 4's 12B model has a file size of 7.7 to 8GB, and in testing it used 8.8GB of VRAM on a 12GB GPU, leaving about 3.4GB (default 4000 context).

The test used Nvidia's management program and dedicated drivers to run models such as Qwen 3.5 9b, Nemotron 3 Nano 4b and Gemma 4 12B locally.

In a test of 49 images, Gemma 4 12B correctly identified 45, and Gemma 4 31B correctly identified 47; both had the problem of misjudging pure cables as chargers, whereas MiniCPM-V did not make this error.

Gemma 4 12B, Qwen3.5 9B, and Ministral 3 8B all release their weights publicly under the Apache 2.0 license.

In memory recall tests, the 12B model answered 82 out of 100 questions correctly and the 31B model answered 98 out of 100, with neither model hallucinating answers.

The experimental setup used a single NVIDIA H100 serving via vLLM, with test models Gemma 4 12B and Gemma 4 31B, and input data consisting of 50 million tokens of real public text.

For small-to-medium models that fit within 32 GB of VRAM, the RTX 5090 leads (approximately 45% on Gemma 4 12B and over 75% on GPT-OSS 20B), but the lead on Qwen 3 27B drops from 47% at Q4 to 23% at Q8.

The author subjectively rated Bonsai's pagoda scene as having the richest detail and leading quality, with Gemma 4 coming second, and Qwen 3.5 9B producing broken output.

Popular choices in the 9B-parameter small model market include Gemma 4 12B, Qwen 3.5 9B, and Ornith 1.5 9B.