yi:6b

OLLAMA GGUF

llama · 6B · Q4_0

Good

Mar 1, 2026 · Apple M4

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

Global Score

77 vs 76

Hardware Fit

100 vs 46

Quality Score

67 vs 89

Hardware

yi:6b gemma4:31b

MachineMacBook AirMacBook Pro

CPUApple M4Apple M4 Max

Cores1016

RAM32 GB64 GB

GPUApple M4Apple M4 Max

OSmacOS 26.3macOS 26.3.1

Archarm64arm64

Power Modebalancedbalanced

Performance

yi:6b gemma4:31b

Tokens/sec27.622.4

First chunkN/A565 ms

TTFT210 ms30.0 s

Load time0.4 s6.9 s

Memory usage3.6 GB43.9 GB

Memory %11%69%

HW Fit Score Breakdown

yi:6b

Speed

40/50

TTFT

30/20

Memory

30/30

gemma4:31b

Speed

30/50

TTFT

0/20

Memory

16/30

Quality

yi:6b

Reasoning

11/20

Coding

12/20

Instruction

13/20

Structured

12/15

Math

13/15

Multilingual

6/10

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

gemma4:31b

Reasoning

16/20

Coding

19/20

Instruction

16/20

Structured

15/15

Math

14/15

Multilingual

9/10

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

View yi:6b details | View gemma4:31b details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest