GPT-OSS-120B:120B
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
67 vs 63
Hardware Fit
21 vs 62
Quality Score
87 vs 63
Hardware
GPT-OSS-120B:120B gemma4:12b
MachineGMKtec NucBox EVO-T2SMacBook Pro
CPUIntel Core™ Ultra X7 358HApple M1 Pro
Cores1610
RAM64 GB16 GB
GPUIntel(R) Arc(TM) B390 GPUApple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
GPT-OSS-120B:120B gemma4:12b
Tokens/sec11.715.3
First chunk4289 ms1142 ms
TTFT9.2 s30.0 s
Load time84.1 s5.4 s
Memory usage61.0 GB7.6 GB
Memory %96%47%
HW Fit Score Breakdown
GPT-OSS-120B:120B
Speed
15/50
TTFT
4/20
Memory
2/30
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
Quality
GPT-OSS-120B:120B
Reasoning
18/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:12b
Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate 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