codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 25, 2026 · Intel Core™ Ultra X7 358H
Global Score
67 vs 68
Hardware Fit
67 vs 21
Quality Score
67 vs 88
Hardware
codestral:22b GPT-120B:120b
MachineNVIDIA NVIDIA_DGX_SparkGMKtec NucBox EVO-T2S
CPUCortex-X925Intel Core™ Ultra X7 358H
Cores2016
RAM122 GB64 GB
GPUDevice 2e12Intel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
codestral:22b GPT-120B:120b
Tokens/sec17.212.1
First chunk129 ms4392 ms
TTFT129 ms8.7 s
Load time11.6 s80.1 s
Memory usage18.9 GB61.0 GB
Memory %16%96%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
GPT-120B:120b
Speed
15/50
TTFT
4/20
Memory
2/30
Quality
codestral:22b
Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
GPT-120B:120b
Reasoning
18/20
Coding
19/20
Instruction
11/20
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