qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
stablelm-2-zephyr-1.6b
LM-STUDIO GGUFstablelm · 1.6B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
75 vs 35
Hardware Fit
50 vs 61
Quality Score
86 vs 24
Hardware
qwen2.5:72b stablelm-2-zephyr-…
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
qwen2.5:72b stablelm-2-zephyr-…
Tokens/sec4.46.5
First chunk529 ms3080 ms
TTFT529 ms3.1 s
Load time49.7 sN/A
Memory usage54.0 GB1.0 GB
Memory %44%6%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
stablelm-2-zephyr-1.6b
Speed
23/50
TTFT
16/20
Memory
22/30
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
stablelm-2-zephyr-1.6b
Reasoning
2/20
Coding
2/20
Instruction
8/20
Structured
6/15
Math
2/15
Multilingual
4/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak 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