microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
qwen3-vl:8b
OLLAMA GGUFqwen3vl · 8.8B · Q4_K_M
Apr 28, 2026 · Intel Xeon® Gold 6230
Global Score
62 vs 72
Hardware Fit
99 vs 89
Quality Score
46 vs 64
Hardware
microsoft/phi-4-mi… qwen3-vl:8b
MachineMacBook AirHP HP Z8 G4 Workstation
CPUApple M4Intel Xeon® Gold 6230
Cores1080
RAM32 GB252 GB
GPUApple M4TU104GL [Quadro RTX 5000]
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
microsoft/phi-4-mi… qwen3-vl:8b
Tokens/sec40.368.2
First chunk289 ms285 ms
TTFT289 ms2.0 s
Load timeN/A42.4 s
Memory usage2.0 GB7.1 GB
Memory %6%3%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3-vl:8b
Speed
50/50
TTFT
9/20
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
qwen3-vl:8b
Reasoning
16/20
Coding
3/20
Instruction
10/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong 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