Back to leaderboard

qwen2.5-math-1.5b-instruct

LM-STUDIO MLX

qwen2 · 1.5B · 4bit

Marginal

Mar 4, 2026 · Apple M4

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
45 vs 85
Hardware Fit
99 vs 64
Quality Score
22 vs 94

Hardware

qwen2.5-math-1.5b-… gemma-4-31b-it-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M4 Max
Cores1016
RAM32 GB128 GB
GPUApple M4Apple M4 Max
OSmacOS 26.3macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen2.5-math-1.5b-… gemma-4-31b-it-mlx
Tokens/sec91.713.6
First chunk205 ms16 ms
TTFT205 ms558 ms
Load timeN/A12.3 s
Memory usage0.8 GB0.0 GB
Memory %3%0%

HW Fit Score Breakdown

qwen2.5-math-1.5b-instr…

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

gemma-4-31b-it-mlx

Speed
14/50
TTFT
20/20
Memory
30/30

Quality

qwen2.5-math-1.5b-instr…

Reasoning
2/20
Coding
0/20
Instruction
3/20
Structured
1/15
Math
14/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

gemma-4-31b-it-mlx

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen2.5-math-1.5b-… details | View gemma-4-31b-it-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