llama3:latest

llama · 8.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

vicuna:13b

llama · 13B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

Global Score

71 vs 59

Hardware Fit

95 vs 84

Quality Score

60 vs 48

Hardware

llama3:latest vicuna:13b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

llama3:latest vicuna:13b

Tokens/sec22.313.4

TTFT295 ms438 ms

Load time0.8 s0.6 s

Memory usage5.6 GB10.3 GB

Memory %18%32%

HW Fit Score Breakdown

llama3:latest

Speed

35/40

TTFT

30/30

Memory

30/30

vicuna:13b

Speed

24/40

TTFT

30/30

Memory

30/30

Quality

llama3:latest

Reasoning

9/20

Coding

9/20

Instruction

15/20

Structured

13/15

Math

4/15

Multilingual

10/10

Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Weak 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 llama3:latest details | View vicuna:13b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running