gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
88 vs 46
Hardware Fit
86 vs 61
Quality Score
89 vs 40
Hardware
gemma4:12b-it-qat llama3.1:8b
MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4 ProCortex-A78AE
Cores126
RAM24 GB7 GB
GPUApple M4 ProIntegrated / Unknown
OSmacOS 15.6.1Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-it-qat llama3.1:8b
Tokens/sec30.07.8
First chunk686 ms1625 ms
TTFT7.1 s1.6 s
Load time5.4 s21.8 s
Memory usage7.1 GB5.2 GB
Memory %30%71%
HW Fit Score Breakdown
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
Quality
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
llama3.1:8b
Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest