qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
75 vs 46
Hardware Fit
50 vs 61
Quality Score
86 vs 40
Hardware
qwen2.5:72b llama3.1:8b
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUCortex-X925Cortex-A78AE
Cores206
RAM122 GB7 GB
GPUDevice 2e12Integrated / Unknown
OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen2.5:72b llama3.1:8b
Tokens/sec4.47.8
First chunk529 ms1625 ms
TTFT529 ms1.6 s
Load time49.7 s21.8 s
Memory usage54.0 GB5.2 GB
Memory %44%71%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
Quality
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
llama3.1:8b
Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor 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