Back to leaderboard

gemma4:12b-mlx

OLLAMA GGUF
Excellent

Jul 4, 2026 · Apple M2 Pro

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 22, 2026 · Apple M1 Pro

Global Score
91 vs 69
Hardware Fit
96 vs 85
Quality Score
89 vs 62

Hardware

gemma4:12b-mlx qwen3.5:4b
MachineMacBook ProMacBook Pro
CPUApple M2 ProApple M1 Pro
Cores1010
RAM16 GB16 GB
GPUApple M2 ProApple M1 Pro
OSmacOS 26.5macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:12b-mlx qwen3.5:4b
Tokens/sec24.736.9
First chunk610 ms474 ms
TTFT610 ms6.9 s
Load time3.6 s2.9 s
Memory usage7.1 GB5.3 GB
Memory %45%33%

HW Fit Score Breakdown

gemma4:12b-mlx

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

qwen3.5:4b

Speed
50/50
TTFT
6/20
Memory
29/30

Quality

gemma4:12b-mlx

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:4b

Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong
View gemma4:12b-mlx details | View qwen3.5:4b 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