Back to leaderboard

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

Global Score
64 vs 58
Hardware Fit
100 vs 68
Quality Score
48 vs 54

Hardware

microsoft/phi-4-mi… qwen3.5-9b-mlx
MachineMac miniMac mini
CPUApple M4 ProApple M4
Cores1410
RAM64 GB24 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… qwen3.5-9b-mlx
Tokens/sec90.316.7
First chunk198 ms23 ms
TTFT198 ms14.1 s
Load timeN/AN/A
Memory usage2.0 GB7.8 GB
Memory %3%33%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

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

qwen3.5-9b-mlx

Speed
36/50
TTFT
3/20
Memory
29/30

Quality

microsoft/phi-4-mini-re…

Reasoning
7/20
Coding
7/20
Instruction
7/20
Structured
7/15
Math
13/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate

qwen3.5-9b-mlx

Reasoning
10/20
Coding
16/20
Instruction
4/20
Structured
9/15
Math
10/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Poor Structured Output: Adequate Math: Adequate Multilingual: Adequate

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