GPT-OSS-120B:120B
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
qwen2-57b:57B
OLLAMA GGUFqwen2moe · 57.4B · Q4_K_M
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
67 vs 69
Hardware Fit
21 vs 51
Quality Score
87 vs 76
Hardware
GPT-OSS-120B:120B qwen2-57b:57B
MachineGMKtec NucBox EVO-T2SHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUIntel Core™ Ultra X7 358HIntel Core™ i7-14700F
Cores1628
RAM64 GB64 GB
GPUIntel(R) Arc(TM) B390 GPUNVIDIA GeForce RTX 5080
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
GPT-OSS-120B:120B qwen2-57b:57B
Tokens/sec11.77.7
First chunk4289 ms940 ms
TTFT9.2 s940 ms
Load time84.1 s0.2 s
Memory usage61.0 GB33.3 GB
Memory %96%52%
HW Fit Score Breakdown
GPT-OSS-120B:120B
Speed
15/50
TTFT
4/20
Memory
2/30
qwen2-57b:57B
Speed
8/50
TTFT
19/20
Memory
24/30
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
qwen2-57b:57B
Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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