qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
58 vs 72
Hardware Fit
82 vs 71
Quality Score
48 vs 72
Hardware
qwen3:14b gemma4:e2b
MachineMacBook ProDell Inc. Inspiron 15 3530
CPUApple M1 MaxIntel Gen Intel® Core™ i7-1355U
Cores1012
RAM32 GB31 GB
GPUApple M1 MaxRaptor Lake-P [Iris Xe Graphics]
OSmacOS 26.3cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
qwen3:14b gemma4:e2b
Tokens/sec24.410.8
First chunk294 ms1408 ms
TTFT7.9 s1.4 s
Load time3.7 s6.0 s
Memory usage13.8 GB7.2 GB
Memory %43%23%
HW Fit Score Breakdown
qwen3:14b
Speed
47/50
TTFT
5/20
Memory
30/30
gemma4:e2b
Speed
21/50
TTFT
20/20
Memory
30/30
Quality
qwen3:14b
Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
gemma4:e2b
Reasoning
10/20
Coding
16/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Weak 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