Back to leaderboard

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score
64 vs 78
Hardware Fit
100 vs 86
Quality Score
48 vs 74

Hardware

microsoft/phi-4-mi… qwen3:8b
MachineMac mini
CPUApple M4 ProAMD Ryzen 9 3900X 12-Core Processor
Cores1424
RAM64 GB64 GB
GPUApple M4 ProNVIDIA GeForce RTX 4060 Ti
OSmacOS 15.7.4Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… qwen3:8b
Tokens/sec90.348.5
First chunk198 ms202 ms
TTFT198 ms4.3 s
Load timeN/A4.2 s
Memory usage2.0 GB5.5 GB
Memory %3%9%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

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

qwen3:8b

Speed
50/50
TTFT
6/20
Memory
30/30

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

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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