phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
qwen3-vl:4b-instruct
OLLAMA GGUFqwen3vl · 4.4B · Q4_K_M
Apr 20, 2026 · Apple M2 Max
Global Score
64 vs 83
Hardware Fit
100 vs 96
Quality Score
48 vs 78
Hardware
phi3:3.8b qwen3-vl:4b-instruct
MachineMacBook AirMac Studio
CPUApple M4Apple M2 Max
Cores1012
RAM32 GB96 GB
GPUApple M4Apple M2 Max
OSmacOS 26.3macOS 26.1
Archarm64arm64
Power Modebalancedbalanced
Performance
phi3:3.8b qwen3-vl:4b-instruct
Tokens/sec42.090.6
First chunkN/A159 ms
TTFT142 ms159 ms
Load time1.1 s5.8 s
Memory usage16.0 GB42.5 GB
Memory %50%44%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3-vl:4b-instruct
Speed
50/50
TTFT
20/20
Memory
26/30
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:4b-instruct
Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong 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