tinyllama:1.1b

llama · 1B · Q4_0

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 86% Compare

Global Score

50 /100

Marginal

Hardware Fit

99/100

Quality

18/100

Get this model

🦙

Ollama

ollama pull tinyllama:1.1b

View on Ollama Library

ollama.com/library/tinyllama

🤗

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: 129.6
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.7
Time to first token How fast the model starts responding — lower is better: 58 ms
Load time Time to load the model into memory before inference: 0.4 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.7 GB (2%)
Total tokens Total number of tokens generated across all benchmark prompts: 1273

Score breakdown

Speed

40/40

Time to first token

30/30

Memory

29/30

Quality

Reasoning

2/20

Coding

0/20

Instruction following

6/20

Structured output

7/15

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: 0.2.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 661c2ed6664bc0bf291c6109cdf37ffcbe2ed5b4ffd43f7b9e20bd7c35184dd2

Interpretation

Hardware fit: 99/100. Overall suitability: MARGINAL (Global 50/100). Category profile: Reasoning: Poor, Coding: Poor, Instruction Following: Weak, Structured Output: Weak, Math: Poor, Multilingual: Weak.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running