mistral:latest
OLLAMA GGUFllama · 7.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
GPT-OSS-120B:120B
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
Global Score
73 vs 67
Hardware Fit
100 vs 21
Quality Score
62 vs 87
Hardware
mistral:latest GPT-OSS-120B:120B
MachineMicro-Star International Co., Ltd. MS-7B79GMKtec NucBox EVO-T2S
CPUAMD Ryzen 5 2600X Six-Core ProcessorIntel Core™ Ultra X7 358H
Cores1216
RAM16 GB64 GB
GPUNVIDIA GeForce GTX 1080Intel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
mistral:latest GPT-OSS-120B:120B
Tokens/sec31.711.7
First chunk102 ms4289 ms
TTFT102 ms9.2 s
Load time14.3 s84.1 s
Memory usage4.8 GB61.0 GB
Memory %30%96%
HW Fit Score Breakdown
mistral:latest
Speed
50/50
TTFT
20/20
Memory
30/30
GPT-OSS-120B:120B
Speed
15/50
TTFT
4/20
Memory
2/30
Quality
mistral:latest
Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
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
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