Back to leaderboard

phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

qwen2.5-1.5b-instruct

LM-STUDIO MLX

qwen2 · 1.5B · 8bit

Good

Mar 4, 2026 · Apple M4

Global Score
38 vs 69
Hardware Fit
100 vs 100
Quality Score
12 vs 56

Hardware

phi-3-mini-128k-in… qwen2.5-1.5b-instr…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

phi-3-mini-128k-in… qwen2.5-1.5b-instr…
Tokens/sec44.058.1
First chunk384 ms211 ms
TTFT385 ms211 ms
Load timeN/AN/A
Memory usage2.0 GB1.5 GB
Memory %6%5%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

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

qwen2.5-1.5b-instruct

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

Quality

phi-3-mini-128k-instruct

Reasoning
3/20
Coding
2/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen2.5-1.5b-instruct

Reasoning
9/20
Coding
10/20
Instruction
10/20
Structured
14/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View phi-3-mini-128k-in… details | View qwen2.5-1.5b-instr… 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