deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

gemma2:2b

gemma2 · 2.6B · Q4_0

Excellent

Mar 2, 2026 · Apple M4

Global Score

73 vs 80

Hardware Fit

100 vs 100

Quality Score

55 vs 67

Hardware

deepseek-v2:16b gemma2:2b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

deepseek-v2:16b gemma2:2b

Tokens/sec56.655.1

TTFT239 ms152 ms

Load time1.2 s0.6 s

Memory usage17.7 GB2.8 GB

Memory %55%9%

HW Fit Score Breakdown

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

gemma2:2b

Speed

40/40

TTFT

30/30

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

gemma2:2b

Reasoning

11/20

Coding

13/20

Instruction

14/20

Structured

15/15

Math

4/15

Multilingual

10/10

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

View deepseek-v2:16b details | View gemma2:2b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running