yi:6b

llama · 6B · Q4_0

Excellent

Mar 1, 2026 · Apple M4

vicuna:13b

llama · 13B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

80 vs 62

Hardware Fit

100 vs 84

Quality Score

67 vs 48

Hardware

yi:6b vicuna:13b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

yi:6b vicuna:13b

Tokens/sec27.613.4

TTFT210 ms438 ms

Load time0.4 s0.6 s

Memory usage3.6 GB10.3 GB

Memory %11%32%

HW Fit Score Breakdown

yi:6b

Speed

40/40

TTFT

30/30

Memory

30/30

vicuna:13b

Speed

24/40

TTFT

30/30

Memory

30/30

Quality

yi:6b

Reasoning

11/20

Coding

12/20

Instruction

13/20

Structured

12/15

Math

13/15

Multilingual

6/10

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

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 yi:6b details | View vicuna:13b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running