Back to leaderboard

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

qwen2.5-math-1.5b-instruct

LM-STUDIO MLX

qwen2 · 1.5B · 4bit

Marginal

Mar 4, 2026 · Apple M4

Global Score
82 vs 45
Hardware Fit
88 vs 99
Quality Score
80 vs 22

Hardware

unsloth-phi-4 qwen2.5-math-1.5b-…
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

unsloth-phi-4 qwen2.5-math-1.5b-…
Tokens/sec27.491.7
First chunk457 ms205 ms
TTFT457 ms205 ms
Load timeN/AN/A
Memory usage7.7 GB0.8 GB
Memory %12%3%

HW Fit Score Breakdown

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

qwen2.5-math-1.5b-instr…

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

Quality

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

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
View unsloth-phi-4 details | View qwen2.5-math-1.5b-… 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