granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score

66 vs 62

Hardware Fit

87 vs 77

Quality Score

57 vs 55

Hardware

granite-3.3-2b-ins… google/gemma-4-e4b

MachineMacBook AirLENOVO 82JQ

CPUApple M4AMD Ryzen 7 5800H

Cores1016

RAM32 GB16 GB

GPUApple M4NVIDIA GeForce RTX 3060 Laptop GPU

OSmacOS 26.3Microsoft Windows 11 家庭版中文版 10.0.26100

Archarm64x64

Power Modebalancedbalanced

Performance

granite-3.3-2b-ins… google/gemma-4-e4b

Tokens/sec18.327.6

First chunk541 ms23 ms

TTFT541 ms480 ms

Load timeN/AN/A

Memory usage4.7 GB13.2 GB

Memory %15%83%

HW Fit Score Breakdown

granite-3.3-2b-instruct

Speed

37/50

TTFT

20/20

Memory

30/30

google/gemma-4-e4b

Speed

48/50

TTFT

20/20

Memory

9/30

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

google/gemma-4-e4b

Reasoning

18/20

Coding

17/20

Instruction

5/20

Structured

3/15

Math

11/15

Multilingual

1/10

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

View granite-3.3-2b-ins… details | View google/gemma-4-e4b 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