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
Aug 25, 2026 · Apple M1 Pro
Global Score
88 vs 72
Hardware Fit
86 vs 77
Quality Score
89 vs 70
Hardware
gemma4:12b-it-qat llama3.1:8b
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1210
RAM24 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 15.6.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-it-qat llama3.1:8b
Tokens/sec30.021.5
First chunk686 ms368 ms
TTFT7.1 s368 ms
Load time5.4 s6.9 s
Memory usage7.1 GB12.9 GB
Memory %30%81%
HW Fit Score Breakdown
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
llama3.1:8b
Speed
47/50
TTFT
20/20
Memory
10/30
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
18/20
Instruction
13/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong 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