qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Global Score
75 vs 82
Hardware Fit
50 vs 93
Quality Score
86 vs 77
Hardware
qwen2.5:72b qwen3.5:4b
MachineNVIDIA NVIDIA_DGX_SparkAZW GTR Pro
CPUCortex-X925AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores2032
RAM122 GB125 GB
GPUDevice 2e12Integrated / Apple Silicon
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archarm64x64
Power Modeperformanceperformance
Performance
qwen2.5:72b qwen3.5:4b
Tokens/sec4.446.8
First chunk529 ms174 ms
TTFT529 ms174 ms
Load time49.7 s5.9 s
Memory usage54.0 GB16.2 GB
Memory %44%13%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
qwen3.5:4b
Speed
43/50
TTFT
20/20
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
qwen3.5:4b
Reasoning
15/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate 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