phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
qwen3-vl:30b
OLLAMA GGUFqwen3vlmoe · 31.1B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
64 vs 80
Hardware Fit
100 vs 98
Quality Score
48 vs 72
Hardware
phi3:3.8b qwen3-vl:30b
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-vl:30b
Tokens/sec42.0208.9
First chunkN/A102 ms
TTFT142 ms684 ms
Load time1.1 s0.1 s
Memory usage16.0 GB22.0 GB
Memory %50%47%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3-vl:30b
Speed
50/50
TTFT
20/20
Memory
28/30
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-vl:30b
Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak 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