gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
deepseek-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
76 vs 69
Hardware Fit
46 vs 100
Quality Score
89 vs 55
Hardware
gemma4:31b deepseek-v2:16b
MachineMacBook ProMacBook Air
CPUApple M4 MaxApple M4
Cores1610
RAM64 GB32 GB
GPUApple M4 MaxApple M4
OSmacOS 26.3.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:31b deepseek-v2:16b
Tokens/sec22.456.6
First chunk565 msN/A
TTFT30.0 s239 ms
Load time6.9 s1.2 s
Memory usage43.9 GB17.7 GB
Memory %69%55%
HW Fit Score Breakdown
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
deepseek-v2:16b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
deepseek-v2:16b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
10/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Adequate 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