vicuna:13b

llama · 13B · Q4_0

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 73% Compare

Global Score

62 /100

Good

Hardware Fit

84/100

Quality

48/100

Get this model

🦙

Ollama

ollama pull vicuna:13b

View on Ollama Library

ollama.com/library/vicuna

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 13.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
Time to first token How fast the model starts responding — lower is better: 438 ms
Load time Time to load the model into memory before inference: 0.6 s
Memory usage RAM consumed during inference — percentage of total system memory: 10.3 GB (32%)
Total tokens Total number of tokens generated across all benchmark prompts: 1098

Score breakdown

Speed

24/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

7/20

Coding

5/20

Instruction following

12/20

Structured output

13/15

Math

3/15

Multilingual

8/10

Category levels

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

Metadata

Spec version: 0.2.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 718340c9559a439a157c3f76e1f7f5e313309758713be633fd640ea15ea8acde

Interpretation

Hardware fit: 84/100. Overall suitability: GOOD (Global 62/100). Category profile: Reasoning: Weak, Coding: Weak, Instruction Following: Adequate, Structured Output: Strong, Math: Poor, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running