microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
unsloth/gemma-4-e4b-it-qat
LM-STUDIO GGUFgemma4 · Q4_K_XL
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
62 vs 79
Hardware Fit
99 vs 69
Quality Score
46 vs 83
Hardware
microsoft/phi-4-mi… unsloth/gemma-4-e4…
MachineMacBook AirDocker Container
CPUApple M4Intel Gen Intel® Core™ i9-11900H
Cores1016
RAM32 GB15 GB
GPUApple M4TigerLake-H GT1 [UHD Graphics]
OSmacOS 26.3Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
microsoft/phi-4-mi… unsloth/gemma-4-e4…
Tokens/sec40.312.1
First chunk289 ms40 ms
TTFT289 ms2.1 s
Load timeN/A7.2 s
Memory usage2.0 GB0.8 GB
Memory %6%6%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
unsloth/gemma-4-e4b-it-…
Speed
22/50
TTFT
17/20
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
unsloth/gemma-4-e4b-it-…
Reasoning
15/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate 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