llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
74 vs 67
Hardware Fit
99 vs 67
Quality Score
63 vs 67
Hardware
llama3.2:3b codestral:22b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperNVIDIA NVIDIA_DGX_Spark
CPUCortex-A78AECortex-X925
Cores620
RAM7 GB122 GB
GPUIntegrated / UnknownDevice 2e12
OSUbuntu 22.04.5 LTSUbuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
llama3.2:3b codestral:22b
Tokens/sec21.117.2
First chunk1032 ms129 ms
TTFT1.0 s129 ms
Load time8.4 s11.6 s
Memory usage2.4 GB18.9 GB
Memory %32%16%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
Quality
llama3.2:3b
Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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