deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 1, 2026 · Apple M4

phi4-mini

Not Rec.

Mar 1, 2026 · Apple M4

Global Score

25 vs 39

Hardware Fit

46 vs 66

Quality Score

11 vs 21

Hardware

deepseek-r1:14b phi4-mini

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

deepseek-r1:14b phi4-mini

Tokens/sec10.821.8

TTFT30.0 s9.6 s

Load time5.3 s3.5 s

Memory usage16.5 GB0.0 GB

Memory %52%0%

HW Fit Score Breakdown

deepseek-r1:14b

Speed

16/40

TTFT

0/30

Memory

30/30

phi4-mini

Speed

31/40

TTFT

5/30

Memory

30/30

Quality

deepseek-r1:14b

Reasoning

1/20

Coding

0/20

Instruction

2/20

Structured

1/15

Math

1/15

Multilingual

6/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate

phi4-mini

Reasoning

11/20

Coding

0/20

Instruction

0/20

Structured

0/15

Math

5/15

Multilingual

5/10

Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Weak

View deepseek-r1:14b details | View phi4-mini details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running