Back to leaderboard

qwen2.5-math-1.5b-instruct

LM-STUDIO MLX

qwen2 · 1.5B · 4bit

Marginal

Mar 4, 2026 · Apple M4

phi3:3.8b

OLLAMA GGUF

phi3 · 3.8B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
45 vs 64
Hardware Fit
99 vs 100
Quality Score
22 vs 48

Hardware

qwen2.5-math-1.5b-… phi3:3.8b
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-… phi3:3.8b
Tokens/sec91.742.0
First chunk205 msN/A
TTFT205 ms142 ms
Load timeN/A1.1 s
Memory usage0.8 GB16.0 GB
Memory %3%50%

HW Fit Score Breakdown

qwen2.5-math-1.5b-instr…

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

phi3:3.8b

Speed
40/50
TTFT
30/20
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

phi3:3.8b

Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
View qwen2.5-math-1.5b-… details | View phi3:3.8b 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