Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

qwen3.6:35b-a3b-coding-nvfp4

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
76 vs 76
Hardware Fit
46 vs 77
Quality Score
89 vs 76

Hardware

gemma4:31b qwen3.6:35b-a3b-co…
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M4 Pro
Cores1614
RAM64 GB48 GB
GPUApple M4 MaxApple M4 Pro
OSmacOS 26.3.1macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:31b qwen3.6:35b-a3b-co…
Tokens/sec22.472.7
First chunk565 ms147 ms
TTFT30.0 s30.0 s
Load time6.9 s5.7 s
Memory usage43.9 GB19.6 GB
Memory %69%41%

HW Fit Score Breakdown

gemma4:31b

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

qwen3.6:35b-a3b-coding-…

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

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

qwen3.6:35b-a3b-coding-…

Reasoning
19/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong 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