qwen2.5-coder:7b

qwen2 · 7.6B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

vicuna:13b

llama · 13B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

70 vs 62

Hardware Fit

94 vs 84

Quality Score

54 vs 48

Hardware

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

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

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

Tokens/sec21.513.4

TTFT290 ms438 ms

Load time0.8 s0.6 s

Memory usage7.6 GB10.3 GB

Memory %24%32%

HW Fit Score Breakdown

qwen2.5-coder:7b

Speed

34/40

TTFT

30/30

Memory

30/30

vicuna:13b

Speed

24/40

TTFT

30/30

Memory

30/30

Quality

qwen2.5-coder:7b

Reasoning

10/20

Coding

0/20

Instruction

13/20

Structured

13/15

Math

9/15

Multilingual

9/10

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

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

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

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running