codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
qwen2.5-0.5b-instruct
LM-STUDIO GGUFqwen2 · 0.5B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
67 vs 53
Hardware Fit
67 vs 89
Quality Score
67 vs 38
Hardware
codestral:22b qwen2.5-0.5b-instr…
MachineNVIDIA NVIDIA_DGX_SparkLENOVO 20BUS00700
CPUCortex-X925Intel Core™ i5-5300U
Cores204
RAM122 GB16 GB
GPUDevice 2e12Intel(R) HD Graphics 5500
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modeperformancebalanced
Performance
codestral:22b qwen2.5-0.5b-instr…
Tokens/sec17.213.2
First chunk129 ms1339 ms
TTFT129 ms1.3 s
Load time11.6 sN/A
Memory usage18.9 GB0.4 GB
Memory %16%2%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
qwen2.5-0.5b-instruct
Speed
41/50
TTFT
20/20
Memory
28/30
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
qwen2.5-0.5b-instruct
Reasoning
5/20
Coding
4/20
Instruction
10/20
Structured
11/15
Math
3/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
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