GPT-OSS-120B:120B
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
orcarouter/Qwen3.8-27B-Uncensored:iq4_xs
OLLAMA GGUFqwen35 · 27.3B · IQ4_XS
Sep 11, 2026 · Intel Core™ i5-10400
Global Score
67 vs 88
Hardware Fit
21 vs 69
Quality Score
87 vs 96
Hardware
GPT-OSS-120B:120B orcarouter/Qwen3.8…
MachineGMKtec NucBox EVO-T2SASUS
CPUIntel Core™ Ultra X7 358HIntel Core™ i5-10400
Cores1612
RAM64 GB16 GB
GPUIntel(R) Arc(TM) B390 GPUTodesk Virtual Display Adapter, AskLink Display Adapter (SDR), OrayIddDriver Device, NVIDIA GeForce RTX 3080
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 10 专业版 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
GPT-OSS-120B:120B orcarouter/Qwen3.8…
Tokens/sec11.739.5
First chunk4289 ms220 ms
TTFT9.2 s3.2 s
Load time84.1 s13.7 s
Memory usage61.0 GB14.2 GB
Memory %96%89%
HW Fit Score Breakdown
GPT-OSS-120B:120B
Speed
15/50
TTFT
4/20
Memory
2/30
orcarouter/Qwen3.8-27B-…
Speed
50/50
TTFT
14/20
Memory
5/30
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
orcarouter/Qwen3.8-27B-…
Reasoning
19/20
Coding
19/20
Instruction
18/20
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest