gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Apr 1, 2026 · Apple M4

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score

87 vs 29

Hardware Fit

83 vs 86

Quality Score

88 vs 4

Hardware

gpt-oss:20b qwen3:4b

MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUApple M4Cortex-A78AE

Cores106

RAM24 GB7 GB

GPUApple M4Integrated / Unknown

OSmacOS 26.3Ubuntu 22.04.5 LTS

Archarm64arm64

Power Modebalancedbalanced

Performance

gpt-oss:20b qwen3:4b

Tokens/sec24.317.9

First chunk529 ms1010 ms

TTFT4.5 s6.4 s

Load time11.2 s9.5 s

Memory usage13.1 GB3.0 GB

Memory %55%40%

HW Fit Score Breakdown

gpt-oss:20b

Speed

49/50

TTFT

11/20

Memory

23/30

qwen3:4b

Speed

50/50

TTFT

8/20

Memory

28/30

Quality

gpt-oss:20b

Reasoning

19/20

Coding

19/20

Instruction

11/20

Structured

14/15

Math

15/15

Multilingual

10/10

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

qwen3:4b

Reasoning

4/20

Coding

0/20

Instruction

0/20

Structured

0/15

Math

0/15

Multilingual

0/10

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

View gpt-oss:20b details | View qwen3:4b 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