codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
qwen3:32b
OLLAMA GGUFqwen3 · 32.8B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
67 vs 79
Hardware Fit
67 vs 59
Quality Score
67 vs 88
Hardware
codestral:22b qwen3:32b
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA_DGX_Spark
CPUCortex-X925Cortex-X925
Cores2020
RAM122 GB122 GB
GPUDevice 2e12Device 2e12
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archarm64arm64
Power Modeperformanceperformance
Performance
codestral:22b qwen3:32b
Tokens/sec17.29.7
First chunk129 ms324 ms
TTFT129 ms324 ms
Load time11.6 s24.5 s
Memory usage18.9 GB26.8 GB
Memory %16%22%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
qwen3:32b
Speed
9/50
TTFT
20/20
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
qwen3:32b
Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
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