tinyllama

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 6, 2026

Top 89% Compare

Global Score

43 /100

Marginal

Hardware Fit

100/100

Quality

19/100

Get this model

🦙

Ollama

ollama pull tinyllama

View on Ollama Library

ollama.com/library/tinyllama

Get it in LM Studio

Search and download models directly from the app

🤗

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: 133.4
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.9
First chunk latency Delay before the first streamed chunk arrives from runtime: 61 ms
Time to first token How fast the model starts responding — lower is better: 61 ms
Load time Time to load the model into memory before inference: 0.5 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.2 GB (1%)
Total tokens Total number of tokens generated across all benchmark prompts: 1323

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

2/20

Coding

2/20

Instruction following

7/20

Structured output

5/15

Math

0/15

Multilingual

3/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.17.6
Model format: GGUF
Hardware profile: BALANCED
Result hash: 773421ce1030a9c45eb142fa387bec6bf3dc9e848e4ca9aa68929be6aa34d50e

Interpretation

Hardware fit: 100/100. Overall suitability: MARGINAL (Global 43/100). Category profile: Reasoning: Poor, Coding: Poor, Instruction Following: Weak, Structured Output: Weak, Math: Poor, Multilingual: Weak.

Bench Environment

Power: AC CPU load: avg 6% (peak 11%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest