granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Excellent

Apr 4, 2026 · AMD RYZEN AI MAX+ 395

Global Score

66 vs 83

Hardware Fit

87 vs 100

Quality Score

57 vs 76

Hardware

granite-3.3-2b-ins… gemma4:e2b

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:e2b

Tokens/sec18.387.9

First chunk541 ms196 ms

TTFT541 ms196 ms

Load timeN/A2.7 s

Memory usage4.7 GB11.2 GB

Memory %15%9%

HW Fit Score Breakdown

granite-3.3-2b-instruct

Speed

37/50

TTFT

20/20

Memory

30/30

gemma4:e2b

Speed

50/50

TTFT

20/20

Memory

30/30

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:e2b

Reasoning

12/20

Coding

16/20

Instruction

15/20

Structured

15/15

Math

8/15

Multilingual

10/10

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

View granite-3.3-2b-ins… details | View gemma4:e2b 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