Back to leaderboard

qwen36-distill-apex

OLLAMA GGUF
Not Rec.

Jul 17, 2026 · Apple M5 Max

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
36 vs 65
Hardware Fit
100 vs 88
Quality Score
8 vs 55

Hardware

qwen36-distill-apex qwen3.5-2b-mlx
MachineMacBook ProMac mini
CPUApple M5 MaxApple M4 Pro
Cores1814
RAM64 GB64 GB
GPUApple M5 MaxApple M4 Pro
OSmacOS 27.0macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen36-distill-apex qwen3.5-2b-mlx
Tokens/sec55.248.9
First chunk210 ms4208 ms
TTFT210 ms4.2 s
Load time4.8 sN/A
Memory usage0.9 GB1.6 GB
Memory %2%3%

HW Fit Score Breakdown

qwen36-distill-apex

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

qwen3.5-2b-mlx

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

Quality

qwen36-distill-apex

Reasoning
8/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

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
View qwen36-distill-apex details | View qwen3.5-2b-mlx details

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