qwen2.5-math-1.5b-instruct
LM-STUDIO MLXqwen2 · 1.5B · 4bit
Mar 4, 2026 · Apple M4
smollm2-1.7b-instruct
LM-STUDIO MLXllama · 1.7B · bf16
Mar 4, 2026 · Apple M4
Global Score
45 vs 65
Hardware Fit
99 vs 99
Quality Score
22 vs 51
Hardware
qwen2.5-math-1.5b-… smollm2-1.7b-instr…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen2.5-math-1.5b-… smollm2-1.7b-instr…
Tokens/sec91.728.5
First chunk205 ms393 ms
TTFT205 ms393 ms
Load timeN/AN/A
Memory usage0.8 GB3.2 GB
Memory %3%10%
HW Fit Score Breakdown
qwen2.5-math-1.5b-instr…
Speed
50/50
TTFT
20/20
Memory
29/30
smollm2-1.7b-instruct
Speed
50/50
TTFT
20/20
Memory
29/30
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
smollm2-1.7b-instruct
Reasoning
10/20
Coding
10/20
Instruction
13/20
Structured
11/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
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