qwen2.5:7b

qwen2 · 7.6B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

85 vs 73

Hardware Fit

95 vs 100

Quality Score

79 vs 55

Hardware

qwen2.5:7b deepseek-v2:16b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5:7b deepseek-v2:16b

Tokens/sec22.256.6

TTFT285 ms239 ms

Load time0.8 s1.2 s

Memory usage7.6 GB17.7 GB

Memory %24%55%

HW Fit Score Breakdown

qwen2.5:7b

Speed

35/40

TTFT

30/30

Memory

30/30

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

qwen2.5:7b

Reasoning

14/20

Coding

18/20

Instruction

16/20

Structured

14/15

Math

8/15

Multilingual

9/10

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

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

View qwen2.5:7b details | View deepseek-v2:16b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running