Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3.5:9b-mlx

OLLAMA GGUF

nvfp4

Excellent

Aug 25, 2026 · Apple M1 Pro

Global Score
76 vs 84
Hardware Fit
46 vs 94
Quality Score
89 vs 80

Hardware

gemma4:31b qwen3.5:9b-mlx
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M1 Pro
Cores1610
RAM64 GB16 GB
GPUApple M4 MaxApple M1 Pro
OSmacOS 26.3.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:31b qwen3.5:9b-mlx
Tokens/sec22.425.0
First chunk565 ms357 ms
TTFT30.0 s357 ms
Load time6.9 s3.8 s
Memory usage43.9 GB8.4 GB
Memory %69%52%

HW Fit Score Breakdown

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

qwen3.5:9b-mlx

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

Quality

gemma4:31b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:9b-mlx

Reasoning
16/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View gemma4:31b 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