deepseek-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Mar 2, 2026 · Apple M4
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
69 vs 91
Hardware Fit
100 vs 96
Quality Score
55 vs 89
Hardware
deepseek-v2:16b gemma4:12b-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M2 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M2 Pro
OSmacOS 26.3macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-v2:16b gemma4:12b-mlx
Tokens/sec56.624.7
First chunkN/A610 ms
TTFT239 ms610 ms
Load time1.2 s3.6 s
Memory usage17.7 GB7.1 GB
Memory %55%45%
HW Fit Score Breakdown
deepseek-v2:16b
Speed
40/50
TTFT
30/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
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
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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