qwen2.5-math-1.5b-instruct
LM-STUDIO MLXqwen2 · 1.5B · 4bit
Mar 4, 2026 · Apple M4
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
45 vs 95
Hardware Fit
99 vs 98
Quality Score
22 vs 94
Hardware
qwen2.5-math-1.5b-… gpt-oss:20b
MachineMacBook AirASUS
CPUApple M4Intel Core™ Ultra 9 285K
Cores1024
RAM32 GB47 GB
GPUApple M4NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen2.5-math-1.5b-… gpt-oss:20b
Tokens/sec91.7239.9
First chunk205 ms180 ms
TTFT205 ms616 ms
Load timeN/A4.3 s
Memory usage0.8 GB13.9 GB
Memory %3%29%
HW Fit Score Breakdown
qwen2.5-math-1.5b-instr…
Speed
50/50
TTFT
20/20
Memory
29/30
gpt-oss:20b
Speed
50/50
TTFT
20/20
Memory
28/30
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
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
15/15
Multilingual
10/10
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