Back to leaderboard

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

gemma4:12b-mlx

OLLAMA GGUF
Not Rec.

Aug 24, 2026 · Apple M1 Pro

Global Score
80 vs 71
Hardware Fit
77 vs 76
Quality Score
81 vs 69

Hardware

qwen3.6:35b-mlx gemma4:12b-mlx
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M1 Pro
Cores1810
RAM48 GB16 GB
GPUApple M5 MaxApple M1 Pro
OSmacOS 26.5.2macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.6:35b-mlx gemma4:12b-mlx
Tokens/sec129.825.0
First chunk77 ms787 ms
TTFT30.0 s30.0 s
Load time1.8 s4.0 s
Memory usage19.7 GB7.1 GB
Memory %41%45%

HW Fit Score Breakdown

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

gemma4:12b-mlx

Speed
50/50
TTFT
0/20
Memory
26/30

Quality

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong

gemma4:12b-mlx

Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate 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