Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

microllm-250m:latest

OLLAMA GGUF

llama · 256.74M · F16

Not Rec.

Jul 5, 2026 · Apple M4 Pro

Global Score
66 vs 34
Hardware Fit
40 vs 100
Quality Score
77 vs 6

Hardware

gemma4:31b microllm-250m:latest
MachineASUSTeK COMPUTER INC. GX10Mac mini
CPUCortex-X925Apple M4 Pro
Cores2012
RAM122 GB24 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 26.5.2
Archarm64arm64
Power Modeperformancebalanced

Performance

gemma4:31b microllm-250m:latest
Tokens/sec10.7291.6
First chunk983 ms50 ms
TTFT20.3 s79 ms
Load time8.8 s0.0 s
Memory usage21.4 GB0.6 GB
Memory %18%2%

HW Fit Score Breakdown

gemma4:31b

Speed
10/50
TTFT
0/20
Memory
30/30

microllm-250m:latest

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

Quality

gemma4:31b

Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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