Back to leaderboard

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
75 vs 78
Hardware Fit
50 vs 54
Quality Score
86 vs 88

Hardware

qwen2.5:72b qwen3-coder:30b-a3…
MachineNVIDIA NVIDIA_DGX_SparkHP HP Pavilion Laptop 15-eh1xxx
CPUCortex-X925AMD Ryzen 5 5500U
Cores2012
RAM122 GB63 GB
GPUDevice 2e12AMD Radeon(TM) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Enterprise LTSC 10.0.19044
Archarm64x64
Power Modeperformancebalanced

Performance

qwen2.5:72b qwen3-coder:30b-a3…
Tokens/sec4.48.0
First chunk529 ms1468 ms
TTFT529 ms1.5 s
Load time49.7 s114.5 s
Memory usage54.0 GB33.5 GB
Memory %44%53%

HW Fit Score Breakdown

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

qwen3-coder:30b-a3b-q8_0

Speed
11/50
TTFT
19/20
Memory
24/30

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-q8_0

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen2.5:72b details | View qwen3-coder:30b-a3… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest