Back to leaderboard

qwen3.5:9b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 26, 2026 · Apple M1 Pro

gemma4:12b-mlx

OLLAMA GGUF
Not Rec.

Aug 24, 2026 · Apple M1 Pro

Global Score
54 vs 71
Hardware Fit
81 vs 76
Quality Score
43 vs 69

Hardware

qwen3.5:9b-mlx gemma4:12b-mlx
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M1 Pro
Cores1010
RAM16 GB16 GB
GPUApple M1 ProApple M1 Pro
OSmacOS 26.6.2macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:9b-mlx gemma4:12b-mlx
Tokens/sec25.225.0
First chunk341 ms787 ms
TTFT6.3 s30.0 s
Load time3.4 s4.0 s
Memory usage8.4 GB7.1 GB
Memory %52%45%

HW Fit Score Breakdown

qwen3.5:9b-mlx

Speed
50/50
TTFT
7/20
Memory
24/30

gemma4:12b-mlx

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

Quality

qwen3.5:9b-mlx

Reasoning
14/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate 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
View qwen3.5:9b-mlx details | View gemma4:12b-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