orca-mini:3b

llama · 3B · Q4_0

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 83% Compare

Global Score

54 /100

Marginal

Hardware Fit

100/100

Quality

24/100

Get this model

🦙

Ollama

ollama pull orca-mini:3b

View on Ollama Library

ollama.com/library/orca-mini

🤗

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: 30.6
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.2
Time to first token How fast the model starts responding — lower is better: 126 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: 2.6 GB (8%)
Total tokens Total number of tokens generated across all benchmark prompts: 995

Score breakdown

Speed

40/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

2/20

Coding

2/20

Instruction following

13/20

Structured output

3/15

Math

1/15

Multilingual

3/10

Category levels

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

Metadata

Spec version: 0.2.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 72ccfe07fb8c7aa14d47e5e7d0c757b6f0dd86cad0ede1a0828d97c0bba29b15

Interpretation

Hardware fit: 100/100. Overall suitability: MARGINAL (Global 54/100). Category profile: Reasoning: Poor, Coding: Poor, Instruction Following: Adequate, Structured Output: Poor, Math: Poor, Multilingual: Weak.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running