gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Mar 10, 2026 · Apple M4

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score

83 vs 47

Hardware Fit

65 vs 53

Quality Score

90 vs 45

Hardware

gpt-oss:20b qwen3:4b

MachineMac miniMacBook Air

CPUApple M4Apple M4

Cores1010

RAM24 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedunknown

Performance

gpt-oss:20b qwen3:4b

Tokens/sec17.111.3

First chunk705 msN/A

TTFT10.2 s9.2 s

Load time23.1 s0.1 s

Memory usage13.1 GB7.2 GB

Memory %55%23%

HW Fit Score Breakdown

gpt-oss:20b

Speed

37/50

TTFT

5/20

Memory

23/30

qwen3:4b

Speed

17/50

TTFT

6/20

Memory

30/30

Quality

gpt-oss:20b

Reasoning

19/20

Coding

18/20

Instruction

13/20

Structured

15/15

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

6/20

Instruction

8/20

Structured

6/15

Math

12/15

Multilingual

9/10

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

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