deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

aya:8b

command-r · 8.0B · F16

Good

Mar 1, 2026 · Apple M4

Global Score

69 vs 66

Hardware Fit

100 vs 92

Quality Score

55 vs 55

Hardware

deepseek-v2:16b aya:8b

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 aya:8b

Tokens/sec56.620.0

TTFT239 ms300 ms

Load time1.2 s0.9 s

Memory usage17.7 GB6.0 GB

Memory %55%19%

HW Fit Score Breakdown

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

aya:8b

Speed

32/40

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

aya:8b

Reasoning

10/20

Coding

6/20

Instruction

13/20

Structured

15/15

Math

2/15

Multilingual

9/10

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

View deepseek-v2:16b details | View aya:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running