Back to leaderboard

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

qwen3.6-27b-mtp

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
64 vs 87
Hardware Fit
100 vs 82
Quality Score
48 vs 89

Hardware

microsoft/phi-4-mi… qwen3.6-27b-mtp
MachineMac miniASUS
CPUApple M4 ProAMD Ryzen 7 7800X3D 8-Core Processor
Cores1416
RAM64 GB31 GB
GPUApple M4 ProNVIDIA GeForce RTX 4090, Raphael
OSmacOS 15.7.4cachyos rolling
Archarm64x64
Power Modebalancedperformance

Performance

microsoft/phi-4-mi… qwen3.6-27b-mtp
Tokens/sec90.343.9
First chunk198 ms10 ms
TTFT198 ms329 ms
Load timeN/AN/A
Memory usage2.0 GB23.1 GB
Memory %3%76%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

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

qwen3.6-27b-mtp

Speed
50/50
TTFT
20/20
Memory
12/30

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

qwen3.6-27b-mtp

Reasoning
18/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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