Back to leaderboard

google/gemma-4-12b-qat

LM-STUDIO GGUF

gemma4 · 12B · Q4_0

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
92 vs 74
Hardware Fit
100 vs 99
Quality Score
89 vs 63

Hardware

google/gemma-4-12b… llama3.2:3b
MachineMicro-Star International Co., Ltd. MS-7E51NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD Ryzen 7 9700X 8-Core ProcessorCortex-A78AE
Cores166
RAM31 GB7 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsIntegrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

google/gemma-4-12b… llama3.2:3b
Tokens/sec90.721.1
First chunk26 ms1032 ms
TTFT127 ms1.0 s
Load timeN/A8.4 s
Memory usage6.7 GB2.4 GB
Memory %21%32%

HW Fit Score Breakdown

google/gemma-4-12b-qat

Speed
50/50
TTFT
20/20
Memory
30/30

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

google/gemma-4-12b-qat

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

llama3.2:3b

Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
View google/gemma-4-12b… details | View llama3.2:3b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest