vicuna:7b

llama · 7B · Q4_0

Good

Mar 1, 2026 · Apple M4

deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

65 vs 73

Hardware Fit

97 vs 100

Quality Score

43 vs 55

Hardware

vicuna: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

vicuna:7b deepseek-v2:16b

Tokens/sec23.456.6

TTFT242 ms239 ms

Load time0.4 s1.2 s

Memory usage5.8 GB17.7 GB

Memory %18%55%

HW Fit Score Breakdown

vicuna:7b

Speed

37/40

TTFT

30/30

Memory

30/30

deepseek-v2:16b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

vicuna:7b

Reasoning

8/20

Coding

4/20

Instruction

10/20

Structured

12/15

Math

2/15

Multilingual

7/10

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

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

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running