Back to leaderboard

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jul 3, 2026 · AMD RYZEN AI MAX+ 395

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

Global Score
94 vs 50
Hardware Fit
91 vs 97
Quality Score
95 vs 30

Hardware

gpt-oss:20b gemma3:270m
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)MacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M3 Pro
Cores3212
RAM64 GB36 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M3 Pro
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200macOS 15.7.5
Archx64arm64
Power Modebalancedbalanced

Performance

gpt-oss:20b gemma3:270m
Tokens/sec48.0239.2
First chunk357 ms127 ms
TTFT2.3 s127 ms
Load time0.2 s0.7 s
Memory usage16.4 GB0.6 GB
Memory %26%2%

HW Fit Score Breakdown

gpt-oss:20b

Speed
50/50
TTFT
11/20
Memory
30/30

gemma3:270m

Speed
50/50
TTFT
20/20
Memory
27/30

Quality

gpt-oss:20b

Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma3:270m

Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
8/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

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