qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
qwen3-coder:30b-a3b-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 18, 2026 · Intel Core™ Ultra 9 285HX
Global Score
75 vs 52
Hardware Fit
50 vs 69
Quality Score
86 vs 45
Hardware
qwen2.5:72b qwen3-coder:30b-a3…
MachineNVIDIA NVIDIA_DGX_SparkMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJG
CPUCortex-X925Intel Core™ Ultra 9 285HX
Cores2024
RAM122 GB63 GB
GPUDevice 2e12Intel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
qwen2.5:72b qwen3-coder:30b-a3…
Tokens/sec4.429.4
First chunk529 ms593 ms
TTFT529 ms593 ms
Load time49.7 s14.2 s
Memory usage54.0 GB42.6 GB
Memory %44%67%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
qwen3-coder:30b-a3b-q4_…
Speed
33/50
TTFT
20/20
Memory
16/30
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-coder:30b-a3b-q4_…
Reasoning
16/20
Coding
18/20
Instruction
0/20
Structured
0/15
Math
11/15
Multilingual
0/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Poor Math: Strong 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