qwen2.5vl:3b
OLLAMA GGUFqwen25vl · 3.8B · Q4_K_M
Oct 31, 2026 · Intel Gen Intel® Core™ i9-12900H
qwen3:1.7b
OLLAMA GGUFqwen3 · 2.0B · Q4_K_M
Oct 11, 2026 · AMD Ryzen 5 5500
Global Score
77 vs 79
Hardware Fit
100 vs 100
Quality Score
67 vs 70
Hardware
qwen2.5vl:3b qwen3:1.7b
MachineMicro-Star International Co., Ltd. Stealth GS77 12UHMicrosoft WSL
CPUIntel Gen Intel® Core™ i9-12900HAMD Ryzen 5 5500
Cores2012
RAM32 GB8 GB
GPUIntel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPUIntegrated / Unknown
OSMicrosoft Windows 11 Home 10.0.26200Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedunknown
Performance
qwen2.5vl:3b qwen3:1.7b
Tokens/sec106.5188.0
First chunk68 ms108 ms
TTFT68 ms1.2 s
Load time17.8 s7.5 s
Memory usage2.8 GB1.6 GB
Memory %9%21%
HW Fit Score Breakdown
qwen2.5vl:3b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3:1.7b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen2.5vl:3b
Reasoning
11/20
Coding
15/20
Instruction
12/20
Structured
14/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3:1.7b
Reasoning
16/20
Coding
7/20
Instruction
14/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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