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

Excellent

Jun 18, 2026 · Intel Core™ Ultra 9 285HX

Global Score
75 vs 90
Hardware Fit
50 vs 89
Quality Score
86 vs 90

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/sec4.443.1
First chunk529 ms957 ms
TTFT529 ms957 ms
Load time49.7 s52.0 s
Memory usage54.0 GB33.6 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
46/50
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
18/20
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