Back to leaderboard

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

falcon-h1-0.5b-instruct

LM-STUDIO GGUF

falcon-h1 · 0.5B · Q4_K_M

Marginal

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score
62 vs 57
Hardware Fit
99 vs 91
Quality Score
46 vs 42

Hardware

microsoft/phi-4-mi… falcon-h1-0.5b-ins…
MachineMacBook AirLENOVO 20BUS00700
CPUApple M4Intel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M4Intel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… falcon-h1-0.5b-ins…
Tokens/sec40.316.3
First chunk289 ms2987 ms
TTFT289 ms3.0 s
Load timeN/AN/A
Memory usage2.0 GB0.3 GB
Memory %6%2%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed
50/50
TTFT
20/20
Memory
29/30

falcon-h1-0.5b-instruct

Speed
48/50
TTFT
16/20
Memory
27/30

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

falcon-h1-0.5b-instruct

Reasoning
8/20
Coding
7/20
Instruction
12/20
Structured
10/15
Math
4/15
Multilingual
1/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Poor

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