Back to leaderboard

gemma4:12b-mlx

OLLAMA GGUF
Excellent

Jul 4, 2026 · Apple M2 Pro

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
81 vs 71
Hardware Fit
82 vs 88
Quality Score
81 vs 63

Hardware

gemma4:12b-mlx qwen3.5-4b-mlx
MachineMacBook ProMacBook Air
CPUApple M2 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M2 ProApple M4
OSmacOS 26.5macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:12b-mlx qwen3.5-4b-mlx
Tokens/sec25.323.1
First chunk761 ms3279 ms
TTFT7.7 s3.3 s
Load time3.6 sN/A
Memory usage7.1 GB2.9 GB
Memory %44%9%

HW Fit Score Breakdown

gemma4:12b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

qwen3.5-4b-mlx

Speed
45/50
TTFT
13/20
Memory
30/30

Quality

gemma4:12b-mlx

Reasoning
16/20
Coding
15/20
Instruction
12/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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
View gemma4:12b-mlx details | View qwen3.5-4b-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