phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
64 vs 84
Hardware Fit
100 vs 97
Quality Score
48 vs 79
Hardware
phi3:3.8b qwen3:8b
MachineMacBook AirASUS
CPUApple M4Intel Core™ Ultra 9 285K
Cores1024
RAM32 GB47 GB
GPUApple M4NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
phi3:3.8b qwen3:8b
Tokens/sec42.0208.0
First chunkN/A82 ms
TTFT142 ms1.3 s
Load time1.1 s1.5 s
Memory usage16.0 GB9.6 GB
Memory %50%20%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3:8b
Speed
50/50
TTFT
18/20
Memory
29/30
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
qwen3:8b
Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate 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