granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score

66 vs 78

Hardware Fit

87 vs 47

Quality Score

57 vs 92

Hardware

granite-3.3-2b-ins… gemma4:31b

MachineMacBook AirAZW GTR Pro

CPUApple M4AMD RYZEN AI MAX+ 395

Cores1032

RAM32 GB125 GB

GPUApple M4Radeon 8060S

OSmacOS 26.3Ubuntu 24.04.4 LTS

Archarm64x64

Power Modebalancedperformance

Performance

granite-3.3-2b-ins… gemma4:31b

Tokens/sec18.39.8

First chunk541 ms873 ms

TTFT541 ms873 ms

Load timeN/A7.0 s

Memory usage4.7 GB68.3 GB

Memory %15%55%

HW Fit Score Breakdown

granite-3.3-2b-instruct

Speed

37/50

TTFT

20/20

Memory

30/30

gemma4:31b

Speed

8/50

TTFT

16/20

Memory

23/30

Quality

granite-3.3-2b-instruct

Reasoning

10/20

Coding

10/20

Instruction

14/20

Structured

14/15

Math

2/15

Multilingual

7/10

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

gemma4:31b

Reasoning

19/20

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 granite-3.3-2b-ins… 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