gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Mar 10, 2026 · Apple M4

smollm2:135m

OLLAMA GGUF

llama · 134.52M · F16

Marginal

Mar 2, 2026 · Apple M4

Global Score

83 vs 41

Hardware Fit

65 vs 100

Quality Score

90 vs 15

Hardware

gpt-oss:20b smollm2:135m

MachineMac miniMacBook Air

CPUApple M4Apple M4

Cores1010

RAM24 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

gpt-oss:20b smollm2:135m

Tokens/sec17.1241.0

First chunk705 msN/A

TTFT10.2 s39 ms

Load time23.1 s0.4 s

Memory usage13.1 GB0.6 GB

Memory %55%2%

HW Fit Score Breakdown

gpt-oss:20b

Speed

37/50

TTFT

5/20

Memory

23/30

smollm2:135m

Speed

40/50

TTFT

30/20

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

smollm2:135m

Reasoning

4/20

Coding

1/20

Instruction

6/20

Structured

2/15

Math

1/15

Multilingual

1/10

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

View gpt-oss:20b details | View smollm2:135m 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