qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
gemma-3-1b-it
LM-STUDIO GGUFgemma3 · 1B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
Global Score
75 vs 59
Hardware Fit
50 vs 76
Quality Score
86 vs 52
Hardware
qwen2.5:72b gemma-3-1b-it
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 gemma-3-1b-it
Tokens/sec4.48.7
First chunk529 ms2078 ms
TTFT529 ms2.1 s
Load time49.7 sN/A
Memory usage54.0 GB0.8 GB
Memory %44%5%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
gemma-3-1b-it
Speed
29/50
TTFT
19/20
Memory
28/30
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
gemma-3-1b-it
Reasoning
4/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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