Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

exaone-3.5-2.4b-instruct-mlx

LM-STUDIO MLX

exaone · 2.4B · 8bit

Good

Mar 4, 2026 · Apple M4

Global Score
66 vs 75
Hardware Fit
91 vs 100
Quality Score
55 vs 64

Hardware

qwen3.8-27b-mlx exaone-3.5-2.4b-in…
MachineMacBook ProMacBook Air
CPUApple M5 MaxApple M4
Cores1810
RAM64 GB32 GB
GPUApple M5 MaxApple M4
OSmacOS 27.0macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx exaone-3.5-2.4b-in…
Tokens/sec33.237.0
First chunk7 ms288 ms
TTFT311 ms288 ms
Load timeN/AN/A
Memory usage0.5 GB2.4 GB
Memory %1%8%

HW Fit Score Breakdown

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
Memory
30/30

exaone-3.5-2.4b-instruc…

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest