gemma4:e4b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
Global Score
90 vs 90
Hardware Fit
86 vs 97
Quality Score
92 vs 87
Hardware
gemma4:e4b-mlx qwen3:14b
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M1 Max
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M1 Max
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:e4b-mlx qwen3:14b
Tokens/sec41.824.0
First chunk359 ms300 ms
TTFT4.2 s300 ms
Load time5.1 s3.6 s
Memory usage7.9 GB13.8 GB
Memory %49%43%
HW Fit Score Breakdown
gemma4:e4b-mlx
Speed
50/50
TTFT
11/20
Memory
25/30
qwen3:14b
Speed
47/50
TTFT
20/20
Memory
30/30
Quality
gemma4:e4b-mlx
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:14b
Reasoning
17/20
Coding
18/20
Instruction
15/20
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