qwen2.5:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 2, 2026 · Apple M4
qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor
Global Score
84 vs 82
Hardware Fit
95 vs 90
Quality Score
79 vs 79
Hardware
qwen2.5:7b qwen3:14b
MachineMacBook AirMicro-Star International Co., Ltd. MS-7C37
CPUApple M4AMD Ryzen 9 3900X 12-Core Processor
Cores1024
RAM32 GB64 GB
GPUApple M4GameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080
OSmacOS 26.3Microsoft Windows 11 专业版 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen2.5:7b qwen3:14b
Tokens/sec22.274.4
First chunkN/A324 ms
TTFT285 ms2.6 s
Load time0.8 s5.1 s
Memory usage7.6 GB9.0 GB
Memory %24%14%
HW Fit Score Breakdown
qwen2.5:7b
Speed
35/50
TTFT
30/20
Memory
30/30
qwen3:14b
Speed
50/50
TTFT
10/20
Memory
30/30
Quality
qwen2.5:7b
Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3:14b
Reasoning
18/20
Coding
11/20
Instruction
17/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong 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