granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

Global Score

66 vs 65

Hardware Fit

87 vs 96

Quality Score

57 vs 52

Hardware

granite-3.3-2b-ins… richardyoung/qwyth…

MachineMacBook AirMac mini

CPUApple M4Apple M4 Pro

Cores1012

RAM32 GB24 GB

GPUApple M4Apple M4 Pro

OSmacOS 26.3macOS 15.6.1

Archarm64arm64

Power Modebalancedbalanced

Performance

granite-3.3-2b-ins… richardyoung/qwyth…

Tokens/sec18.325.3

First chunk541 ms397 ms

TTFT541 ms397 ms

Load timeN/A6.3 s

Memory usage4.7 GB8.3 GB

Memory %15%34%

HW Fit Score Breakdown

granite-3.3-2b-instruct

Speed

37/50

TTFT

20/20

Memory

30/30

richardyoung/qwythos-9b…

Speed

47/50

TTFT

20/20

Memory

29/30

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

richardyoung/qwythos-9b…

Reasoning

18/20

Coding

13/20

Instruction

6/20

Structured

0/15

Math

14/15

Multilingual

1/10

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

View granite-3.3-2b-ins… details | View richardyoung/qwyth… 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