mlx-community/quantized-gemma-2b-it
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen2.5-math-1.5b-instruct
LM-STUDIO MLXqwen2 · 1.5B · 4bit
Mar 4, 2026 · Apple M4
Global Score
45 vs 45
Hardware Fit
100 vs 99
Quality Score
21 vs 22
Hardware
mlx-community/quan… qwen2.5-math-1.5b-…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/quan… qwen2.5-math-1.5b-…
Tokens/sec44.491.7
First chunk336 ms205 ms
TTFT336 ms205 ms
Load timeN/AN/A
Memory usage0.1 GB0.8 GB
Memory %0%3%
HW Fit Score Breakdown
mlx-community/quantized…
Speed
50/50
TTFT
20/20
Memory
30/30
qwen2.5-math-1.5b-instr…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
mlx-community/quantized…
Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Poor
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
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