qwen3.5-4b-mlx
LM-STUDIO MLXqwen3_5 · 4B · 4bit
Mar 3, 2026 · Apple M4
dolphin-phi:2.7b
OLLAMA GGUFphi2 · 3B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
71 vs 61
Hardware Fit
88 vs 100
Quality Score
63 vs 44
Hardware
qwen3.5-4b-mlx dolphin-phi:2.7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-4b-mlx dolphin-phi:2.7b
Tokens/sec23.156.1
First chunk3279 msN/A
TTFT3.3 s108 ms
Load timeN/A0.4 s
Memory usage2.9 GB2.2 GB
Memory %9%7%
HW Fit Score Breakdown
qwen3.5-4b-mlx
Speed
45/50
TTFT
13/20
Memory
30/30
dolphin-phi:2.7b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5-4b-mlx
Reasoning
15/20
Coding
16/20
Instruction
6/20
Structured
6/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
dolphin-phi:2.7b
Reasoning
10/20
Coding
6/20
Instruction
12/20
Structured
2/15
Math
9/15
Multilingual
5/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Poor Math: Adequate Multilingual: Adequate
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