mistral-small:24b
OLLAMA GGUFllama · 23.6B · Q4_K_M
Jun 26, 2026 · Cortex-X925
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
75 vs 67
Hardware Fit
64 vs 67
Quality Score
80 vs 67
Hardware
mistral-small:24b codestral:22b
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
mistral-small:24b codestral:22b
Tokens/sec14.317.2
First chunk327 ms129 ms
TTFT327 ms129 ms
Load time12.0 s11.6 s
Memory usage18.5 GB18.9 GB
Memory %15%16%
HW Fit Score Breakdown
mistral-small:24b
Speed
14/50
TTFT
20/20
Memory
30/30
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
Quality
mistral-small:24b
Reasoning
16/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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
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