gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
deepseek-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
71 vs 69
Hardware Fit
76 vs 100
Quality Score
69 vs 55
Hardware
gemma4:12b-mlx deepseek-v2:16b
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b-mlx deepseek-v2:16b
Tokens/sec25.056.6
First chunk787 msN/A
TTFT30.0 s239 ms
Load time4.0 s1.2 s
Memory usage7.1 GB17.7 GB
Memory %45%55%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
deepseek-v2:16b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
gemma4:12b-mlx
Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate 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