qwen2.5-math-1.5b-instruct
LM-STUDIO MLXqwen2 · 1.5B · 4bit
Mar 4, 2026 · Apple M4
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
45 vs 78
Hardware Fit
99 vs 47
Quality Score
22 vs 92
Hardware
qwen2.5-math-1.5b-… gemma4:31b
MachineMacBook AirAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M4Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
qwen2.5-math-1.5b-… gemma4:31b
Tokens/sec91.79.8
First chunk205 ms873 ms
TTFT205 ms873 ms
Load timeN/A7.0 s
Memory usage0.8 GB68.3 GB
Memory %3%55%
HW Fit Score Breakdown
qwen2.5-math-1.5b-instr…
Speed
50/50
TTFT
20/20
Memory
29/30
gemma4:31b
Speed
8/50
TTFT
16/20
Memory
23/30
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
gemma4:31b
Reasoning
19/20
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
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest