granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

nous-hermes2:latest

OLLAMA GGUF

llama · 11B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

66 vs 68

Hardware Fit

87 vs 87

Quality Score

57 vs 60

Hardware

granite-3.3-2b-ins… nous-hermes2:latest

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

granite-3.3-2b-ins… nous-hermes2:latest

Tokens/sec18.315.9

First chunk541 msN/A

TTFT541 ms345 ms

Load timeN/A0.4 s

Memory usage4.7 GB6.6 GB

Memory %15%21%

HW Fit Score Breakdown

granite-3.3-2b-instruct

Speed

37/50

TTFT

20/20

Memory

30/30

nous-hermes2:latest

Speed

27/50

TTFT

30/20

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

nous-hermes2:latest

Reasoning

11/20

Coding

9/20

Instruction

12/20

Structured

15/15

Math

4/15

Multilingual

9/10

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

View granite-3.3-2b-ins… details | View nous-hermes2:latest 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