granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

GPT-OSS-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 18, 2026 · Intel Core™ i7-14700F

Global Score

66 vs 93

Hardware Fit

87 vs 92

Quality Score

57 vs 93

Hardware

granite-3.3-2b-ins… GPT-OSS-20B:20b

MachineMacBook AirHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC

CPUApple M4Intel Core™ i7-14700F

Cores1028

RAM32 GB128 GB

GPUApple M4NVIDIA GeForce RTX 5080

OSmacOS 26.3Microsoft Windows 11 Enterprise 10.0.26200

Archarm64x64

Power Modebalancedbalanced

Performance

granite-3.3-2b-ins… GPT-OSS-20B:20b

Tokens/sec18.3178.6

First chunk541 ms695 ms

TTFT541 ms1.4 s

Load timeN/A31.2 s

Memory usage4.7 GB11.9 GB

Memory %15%9%

HW Fit Score Breakdown

granite-3.3-2b-instruct

Speed

37/50

TTFT

20/20

Memory

30/30

GPT-OSS-20B:20b

Speed

50/50

TTFT

12/20

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

GPT-OSS-20B:20b

Reasoning

19/20

Coding

18/20

Instruction

16/20

Structured

15/15

Math

15/15

Multilingual

10/10

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

View granite-3.3-2b-ins… details | View GPT-OSS-20B:20b 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