exaone-3.5-2.4b-instruct-mlx
LM-STUDIO MLXexaone · 2.4B · 8bit
Mar 4, 2026 · Apple M4
qwen3.5-4b-mlx
LM-STUDIO MLXqwen3_5 · 4B · 4bit
Mar 3, 2026 · Apple M4
Global Score
75 vs 71
Hardware Fit
100 vs 88
Quality Score
64 vs 63
Hardware
exaone-3.5-2.4b-in… qwen3.5-4b-mlx
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
exaone-3.5-2.4b-in… qwen3.5-4b-mlx
Tokens/sec37.023.1
First chunk288 ms3279 ms
TTFT288 ms3.3 s
Load timeN/AN/A
Memory usage2.4 GB2.9 GB
Memory %8%9%
HW Fit Score Breakdown
exaone-3.5-2.4b-instruc…
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-4b-mlx
Speed
45/50
TTFT
13/20
Memory
30/30
Quality
exaone-3.5-2.4b-instruc…
Reasoning
9/20
Coding
13/20
Instruction
15/20
Structured
14/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
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
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