deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

starcoder2:7b

starcoder2 · 7B · Q4_0

Not Rec.

Mar 2, 2026 · Apple M4

Global Score

69 vs 35

Hardware Fit

100 vs 97

Quality Score

55 vs 8

Hardware

deepseek-v2:16b starcoder2:7b

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 starcoder2:7b

Tokens/sec56.623.8

TTFT239 ms251 ms

Load time1.2 s0.4 s

Memory usage17.7 GB6.3 GB

Memory %55%20%

HW Fit Score Breakdown

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

starcoder2:7b

Speed

37/40

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

starcoder2:7b

Reasoning

0/20

Coding

1/20

Instruction

4/20

Structured

2/15

Math

0/15

Multilingual

1/10

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

View deepseek-v2:16b details | View starcoder2:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running