Back to leaderboard

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen36-distill-apex

OLLAMA GGUF
Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
62 vs 36
Hardware Fit
99 vs 100
Quality Score
46 vs 8

Hardware

microsoft/phi-4-mi… qwen36-distill-apex
MachineMacBook AirMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM32 GB64 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… qwen36-distill-apex
Tokens/sec40.355.2
First chunk289 ms210 ms
TTFT289 ms210 ms
Load timeN/A4.8 s
Memory usage2.0 GB0.9 GB
Memory %6%2%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

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

qwen36-distill-apex

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

Quality

microsoft/phi-4-mini-re…

Reasoning
7/20
Coding
6/20
Instruction
7/20
Structured
7/15
Math
12/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate

qwen36-distill-apex

Reasoning
8/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View microsoft/phi-4-mi… details | View qwen36-distill-apex 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