phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
64 vs 83
Hardware Fit
100 vs 99
Quality Score
48 vs 76
Hardware
phi3:3.8b qwen3.5:4b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
phi3:3.8b qwen3.5:4b
Tokens/sec42.036.6
First chunkN/A204 ms
TTFT142 ms204 ms
Load time1.1 s2.7 s
Memory usage16.0 GB5.3 GB
Memory %50%33%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3.5:4b
Speed
50/50
TTFT
20/20
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
qwen3.5:4b
Reasoning
16/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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