microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
nemotron-3-super:latest
OLLAMA GGUFnemotron_h_moe · 123.6B · Q4_K_M
Oct 3, 2026 · Cortex-X925
Global Score
62 vs 74
Hardware Fit
99 vs 50
Quality Score
46 vs 84
Hardware
microsoft/phi-4-mi… nemotron-3-super:l…
MachineMacBook AirNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.5 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
microsoft/phi-4-mi… nemotron-3-super:l…
Tokens/sec40.321.8
First chunk289 ms420 ms
TTFT289 ms2.2 s
Load timeN/A12.4 s
Memory usage2.0 GB79.5 GB
Memory %6%65%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
nemotron-3-super:latest
Speed
23/50
TTFT
10/20
Memory
17/30
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
nemotron-3-super:latest
Reasoning
17/20
Coding
18/20
Instruction
11/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong 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