gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
gemma4:26b-nvfp4
OLLAMA GGUFnvfp4
May 25, 2026 · Apple M4 Pro
Global Score
81 vs 85
Hardware Fit
59 vs 80
Quality Score
91 vs 87
Hardware
gpt-oss:20b gemma4:26b-nvfp4
MachineGMKtec NucBox EVO-T2SMacBook Pro
CPUIntel Core™ Ultra X7 358HApple M4 Pro
Cores1614
RAM64 GB48 GB
GPUIntel(R) Arc(TM) B390 GPUApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.4.1
Archx64arm64
Power Modebalancedbalanced
Performance
gpt-oss:20b gemma4:26b-nvfp4
Tokens/sec19.165.7
First chunk1985 ms233 ms
TTFT11.1 s30.0 s
Load time7.7 s5.0 s
Memory usage12.9 GB15.2 GB
Memory %20%32%
HW Fit Score Breakdown
gpt-oss:20b
Speed
26/50
TTFT
3/20
Memory
30/30
gemma4:26b-nvfp4
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:26b-nvfp4
Reasoning
17/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest