yi:6b

llama · 6B · Q4_0

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 1, 2026

Top 6% Compare

Global Score

80 /100

Excellent

Hardware Fit

100/100

Quality

67/100

Get this model

🦙

Ollama

ollama pull yi:6b

View on Ollama Library

ollama.com/library/yi

🤗

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: 27.6
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.2
Time to first token How fast the model starts responding — lower is better: 210 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: 3.6 GB (11%)
Total tokens Total number of tokens generated across all benchmark prompts: 1204

Score breakdown

Speed

40/40

Time to first token

30/30

Memory

30/30

Quality

Reasoning

11/20

Coding

12/20

Instruction following

13/20

Structured output

12/15

Math

13/15

Multilingual

6/10

Category levels

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

Metadata

Spec version: 0.2.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: d9615a45eebc43b4c99cc60bbe4dd0674ba2b05432d295092eabcaa90a4c080d

Interpretation

Hardware fit: 100/100. Overall suitability: EXCELLENT (Global 80/100). Category profile: Reasoning: Adequate, Coding: Adequate, Instruction Following: Adequate, Structured Output: Strong, Math: Strong, Multilingual: Adequate.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running