codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
67 vs 93
Hardware Fit
67 vs 93
Quality Score
67 vs 93
Hardware
codestral:22b GPT-20B:20b
MachineNVIDIA NVIDIA_DGX_SparkHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUCortex-X925Intel Core™ i7-14700F
Cores2028
RAM122 GB128 GB
GPUDevice 2e12NVIDIA GeForce RTX 5080
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
codestral:22b GPT-20B:20b
Tokens/sec17.2177.5
First chunk129 ms558 ms
TTFT129 ms1.2 s
Load time11.6 s8.2 s
Memory usage18.9 GB11.9 GB
Memory %16%9%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
GPT-20B:20b
Speed
50/50
TTFT
13/20
Memory
30/30
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-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
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