Back to leaderboard

gemma4:e2b-mlx

OLLAMA GGUF
Not Rec.

Aug 26, 2026 · Apple M1 Pro

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

Global Score
88 vs 77
Hardware Fit
79 vs 67
Quality Score
92 vs 81

Hardware

gemma4:e2b-mlx qwen3.5-9b-mlx
MachineMacBook ProMac mini
CPUApple M1 ProApple M4 Pro
Cores1014
RAM16 GB64 GB
GPUApple M1 ProApple M4 Pro
OSmacOS 26.6.2macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:e2b-mlx qwen3.5-9b-mlx
Tokens/sec72.820.3
First chunk134 ms4216 ms
TTFT30.0 s4.2 s
Load time2.6 sN/A
Memory usage5.7 GB5.6 GB
Memory %36%9%

HW Fit Score Breakdown

gemma4:e2b-mlx

Speed
50/50
TTFT
0/20
Memory
29/30

qwen3.5-9b-mlx

Speed
29/50
TTFT
8/20
Memory
30/30

Quality

gemma4:e2b-mlx

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-9b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View gemma4:e2b-mlx details | View qwen3.5-9b-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