Back to leaderboard

gemma4:latest

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Jun 5, 2026 · AMD Ryzen 7 5800H

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
89 vs 75
Hardware Fit
83 vs 50
Quality Score
92 vs 86

Hardware

gemma4:latest qwen2.5:72b
MachineLENOVO 82JQNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 7 5800HCortex-X925
Cores1620
RAM16 GB122 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUDevice 2e12
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

gemma4:latest qwen2.5:72b
Tokens/sec46.34.4
First chunk824 ms529 ms
TTFT3.8 s529 ms
Load time21.0 s49.7 s
Memory usage8.9 GB54.0 GB
Memory %56%44%

HW Fit Score Breakdown

gemma4:latest

Speed
50/50
TTFT
11/20
Memory
22/30

qwen2.5:72b

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

Quality

gemma4:latest

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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

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