cogito:3b

llama · 3.6B · Q4_K_M

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 6, 2026

Top 52% Compare

Global Score

67 /100

Good

Hardware Fit

100/100

Quality

53/100

Get this model

🦙

Ollama

ollama pull cogito:3b

View on Ollama Library

ollama.com/library/cogito

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: 45.6
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.3
First chunk latency Delay before the first streamed chunk arrives from runtime: 177 ms
Time to first token How fast the model starts responding — lower is better: 177 ms
Load time Time to load the model into memory before inference: 0.8 s
Memory usage RAM consumed during inference — percentage of total system memory: 7.0 GB (22%)
Total tokens Total number of tokens generated across all benchmark prompts: 933

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

6/20

Coding

8/20

Instruction following

13/20

Structured output

15/15

Math

2/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.17.6
Model format: GGUF
Hardware profile: BALANCED
Result hash: c4cead45fb8ddc5ef36a14caa586108c5ac2512e2d76638f1d8d08e351f97b57

Interpretation

Hardware fit: 100/100. Overall suitability: GOOD (Global 67/100). Category profile: Reasoning: Weak, Coding: Weak, Instruction Following: Adequate, Structured Output: Strong, Math: Poor, Multilingual: Strong.

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