Back to leaderboard

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

google/gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_0

Excellent

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
64 vs 82
Hardware Fit
100 vs 56
Quality Score
48 vs 93

Hardware

microsoft/phi-4-mi… google/gemma-4-26b…
MachineMac miniDocker Container
CPUApple M4 ProIntel Gen Intel® Core™ i9-11900H
Cores1416
RAM64 GB15 GB
GPUApple M4 ProTigerLake-H GT1 [UHD Graphics]
OSmacOS 15.7.4Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

microsoft/phi-4-mi… google/gemma-4-26b…
Tokens/sec90.312.0
First chunk198 ms86 ms
TTFT198 ms2.8 s
Load timeN/A57.2 s
Memory usage2.0 GB9.1 GB
Memory %3%59%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

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

google/gemma-4-26b-a4b-…

Speed
22/50
TTFT
14/20
Memory
20/30

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

google/gemma-4-26b-a4b-…

Reasoning
17/20
Coding
19/20
Instruction
20/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View microsoft/phi-4-mi… details | View google/gemma-4-26b… 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