qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
qwen3.5:2b
OLLAMA GGUFqwen35 · 2.3B · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
75 vs 13
Hardware Fit
50 vs 41
Quality Score
86 vs 1
Hardware
qwen2.5:72b qwen3.5:2b
MachineNVIDIA NVIDIA_DGX_SparkLENOVO 20L7CTO1WW
CPUCortex-X925Intel Core™ i5-8350U
Cores208
RAM122 GB23 GB
GPUDevice 2e12Kaby Lake-R GT2 [UHD Graphics 620]
OSUbuntu 24.04.4 LTSFedora Linux 43
Archarm64x64
Power Modeperformancelow-power
Performance
qwen2.5:72b qwen3.5:2b
Tokens/sec4.44.5
First chunk529 ms1413 ms
TTFT529 ms31.1 s
Load time49.7 s7.1 s
Memory usage54.0 GB3.8 GB
Memory %44%16%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
qwen3.5:2b
Speed
11/50
TTFT
0/20
Memory
30/30
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
qwen3.5:2b
Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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