deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 1, 2026 · Apple M4

Global Score

73 vs 25

Hardware Fit

100 vs 46

Quality Score

55 vs 11

Hardware

deepseek-v2:16b deepseek-r1:14b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedunknown

Performance

deepseek-v2:16b deepseek-r1:14b

Tokens/sec56.610.8

TTFT239 ms30.0 s

Load time1.2 s5.3 s

Memory usage17.7 GB16.5 GB

Memory %55%52%

HW Fit Score Breakdown

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

deepseek-r1:14b

Speed

16/40

TTFT

0/30

Memory

30/30

Quality

deepseek-v2:16b

Reasoning

7/20

Coding

9/20

Instruction

13/20

Structured

10/15

Math

8/15

Multilingual

8/10

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

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

View deepseek-v2:16b details | View deepseek-r1:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running