granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

laguna-xs-2.1

OLLAMA GGUF

Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score

66 vs 84

Hardware Fit

87 vs 100

Quality Score

57 vs 77

Hardware

granite-3.3-2b-ins… laguna-xs-2.1

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 Modebalancedlow-power

Performance

granite-3.3-2b-ins… laguna-xs-2.1

Tokens/sec18.365.9

First chunk541 ms281 ms

TTFT541 ms281 ms

Load timeN/A9.9 s

Memory usage4.7 GB30.1 GB

Memory %15%24%

HW Fit Score Breakdown

granite-3.3-2b-instruct

Speed

37/50

TTFT

20/20

Memory

30/30

laguna-xs-2.1

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

laguna-xs-2.1

Reasoning

8/20

Coding

18/20

Instruction

16/20

Structured

14/15

Math

11/15

Multilingual

10/10

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

View granite-3.3-2b-ins… details | View laguna-xs-2.1 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