GPT-OSS-120B:120B
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
gemma-3-4b-it-q4-k-m
OLLAMA GGUFllama · 4B · Q4_K_M
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
67 vs 80
Hardware Fit
21 vs 100
Quality Score
87 vs 71
Hardware
GPT-OSS-120B:120B gemma-3-4b-it-q4-k-m
MachineGMKtec NucBox EVO-T2SMac Pro
CPUIntel Core™ Ultra X7 358HIntel Core™ i5-10400
Cores1612
RAM64 GB32 GB
GPUIntel(R) Arc(TM) B390 GPUAMD Radeon RX 6700 XT
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.5.1
Archx64x64
Power Modebalancedbalanced
Performance
GPT-OSS-120B:120B gemma-3-4b-it-q4-k-m
Tokens/sec11.775.0
First chunk4289 ms136 ms
TTFT9.2 s136 ms
Load time84.1 s0.0 s
Memory usage61.0 GB0.8 GB
Memory %96%3%
HW Fit Score Breakdown
GPT-OSS-120B:120B
Speed
15/50
TTFT
4/20
Memory
2/30
gemma-3-4b-it-q4-k-m
Speed
50/50
TTFT
20/20
Memory
30/30
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
gemma-3-4b-it-q4-k-m
Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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