Back to leaderboard

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Not Rec.

Apr 3, 2026 · Apple M4

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Jul 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
33 vs 94
Hardware Fit
50 vs 91
Quality Score
25 vs 95

Hardware

gemma4:26b gpt-oss:20b
MachineMac miniFramework Desktop (AMD Ryzen AI Max 300 Series)
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM24 GB64 GB
GPUApple M4AMD Radeon(TM) 8060S Graphics
OSmacOS 26.3Microsoft Windows 11 Pro for Workstations 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

gemma4:26b gpt-oss:20b
Tokens/sec20.048.0
First chunk941 ms357 ms
TTFT30.0 s2.3 s
Load time0.2 s0.2 s
Memory usage20.3 GB16.4 GB
Memory %85%26%

HW Fit Score Breakdown

gemma4:26b

Speed
42/50
TTFT
0/20
Memory
8/30

gpt-oss:20b

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

Quality

gemma4:26b

Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

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

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