vicuna:13b

llama · 13B · Q4_0

Good

Mar 1, 2026 · Apple M4

qwen2.5-coder:7b

qwen2 · 7.6B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

Global Score

62 vs 81

Hardware Fit

84 vs 95

Quality Score

48 vs 72

Hardware

vicuna:13b qwen2.5-coder:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

vicuna:13b qwen2.5-coder:7b

Tokens/sec13.422.1

TTFT438 ms285 ms

Load time0.6 s0.8 s

Memory usage10.3 GB7.6 GB

Memory %32%24%

HW Fit Score Breakdown

vicuna:13b

Speed

24/40

TTFT

30/30

Memory

30/30

qwen2.5-coder:7b

Speed

35/40

TTFT

30/30

Memory

30/30

Quality

vicuna:13b

Reasoning

7/20

Coding

5/20

Instruction

12/20

Structured

13/15

Math

3/15

Multilingual

8/10

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

qwen2.5-coder:7b

Reasoning

10/20

Coding

18/20

Instruction

13/20

Structured

13/15

Math

9/15

Multilingual

9/10

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

View vicuna:13b details | View qwen2.5-coder:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running