Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
80 vs 65
Hardware Fit
52 vs 88
Quality Score
92 vs 55

Hardware

qwen/qwen3.8-27b qwen3.5-2b-mlx
MachineMacBook ProMac mini
CPUApple M4 MaxApple M4 Pro
Cores1614
RAM128 GB64 GB
GPUApple M4 MaxApple M4 Pro
OSmacOS 26.5.2macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.8-27b qwen3.5-2b-mlx
Tokens/sec16.148.9
First chunk14 ms4208 ms
TTFT5.8 s4.2 s
Load time8.5 sN/A
Memory usage0.0 GB1.6 GB
Memory %0%3%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
17/50
TTFT
5/20
Memory
30/30

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

Quality

qwen/qwen3.8-27b

Reasoning
19/20
Coding
16/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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