microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 5, 2026 · Apple M4 Pro
google/gemma-4-12b-qat
LM-STUDIO GGUFgemma4 · 12B · Q4_0
Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
64 vs 92
Hardware Fit
100 vs 100
Quality Score
48 vs 89
Hardware
microsoft/phi-4-mi… google/gemma-4-12b…
MachineMac miniMicro-Star International Co., Ltd. MS-7E51
CPUApple M4 ProAMD Ryzen 7 9700X 8-Core Processor
Cores1416
RAM64 GB31 GB
GPUApple M4 ProNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 15.7.4Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
microsoft/phi-4-mi… google/gemma-4-12b…
Tokens/sec90.390.7
First chunk198 ms26 ms
TTFT198 ms127 ms
Load timeN/AN/A
Memory usage2.0 GB6.7 GB
Memory %3%21%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
30/30
google/gemma-4-12b-qat
Speed
50/50
TTFT
20/20
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
google/gemma-4-12b-qat
Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest