Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

microllm-250m:latest

OLLAMA GGUF

llama · 256.74M · F16

Not Rec.

Jul 5, 2026 · Apple M4 Pro

Global Score
76 vs 34
Hardware Fit
46 vs 100
Quality Score
89 vs 6

Hardware

gemma4:31b microllm-250m:latest
MachineMacBook ProMac mini
CPUApple M4 MaxApple M4 Pro
Cores1612
RAM64 GB24 GB
GPUApple M4 MaxApple M4 Pro
OSmacOS 26.3.1macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:31b microllm-250m:latest
Tokens/sec22.4291.6
First chunk565 ms50 ms
TTFT30.0 s79 ms
Load time6.9 s0.0 s
Memory usage43.9 GB0.6 GB
Memory %69%2%

HW Fit Score Breakdown

gemma4:31b

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

microllm-250m:latest

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

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

microllm-250m:latest

Reasoning
1/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

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