Back to leaderboard

qwen2.5-vl:7b

OLLAMA GGUF

qwen2vl · 7.6B · Q4_K_M

Excellent

Nov 8, 2026 · AMD Ryzen 7 8845HS

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
84 vs 81
Hardware Fit
100 vs 100
Quality Score
77 vs 73

Hardware

qwen2.5-vl:7b gemma3n:latest
MachineLENOVO 83DHSupermicro AS -2015HS-TNR
CPUAMD Ryzen 7 8845HSAMD EPYC 9654P 96-Core Processor
Cores1664
RAM15 GB128 GB
GPUNVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M GraphicsGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSMicrosoft Windows 11 Home Single Language 10.0.26300Ubuntu 24.04.3 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen2.5-vl:7b gemma3n:latest
Tokens/sec29.9108.7
First chunk89 ms333 ms
TTFT89 ms333 ms
Load time10.9 s4.5 s
Memory usage4.8 GB8.6 GB
Memory %31%7%

HW Fit Score Breakdown

qwen2.5-vl:7b

Speed
50/50
TTFT
20/20
Memory
30/30

gemma3n:latest

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

qwen2.5-vl:7b

Reasoning
16/20
Coding
14/20
Instruction
13/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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