phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
64 vs 68
Hardware Fit
100 vs 59
Quality Score
48 vs 72
Hardware
phi3:3.8b qwen2.5-coder:7b
MachineMacBook AirASUS
CPUApple M4Intel Gen Intel® Core™ i7-13700K
Cores1024
RAM32 GB64 GB
GPUApple M4NVIDIA GeForce RTX 3070
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
phi3:3.8b qwen2.5-coder:7b
Tokens/sec42.034.4
First chunkN/A1991 ms
TTFT142 ms2.0 s
Load time1.1 s40.6 s
Memory usage16.0 GB5.0 GB
Memory %50%8%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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