qwen3-vl:2b
OLLAMA GGUFqwen3vl · 2.1B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
62 vs 68
Hardware Fit
99 vs 59
Quality Score
46 vs 72
Hardware
qwen3-vl:2b qwen2.5-coder:7b
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i7-13700K
Cores3224
RAM125 GB64 GB
GPUAMD Radeon 8060SNVIDIA GeForce RTX 3070
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerunknown
Performance
qwen3-vl:2b qwen2.5-coder:7b
Tokens/sec127.434.4
First chunk101 ms1991 ms
TTFT630 ms2.0 s
Load time5.9 s40.6 s
Memory usage33.2 GB5.0 GB
Memory %27%8%
HW Fit Score Breakdown
qwen3-vl:2b
Speed
50/50
TTFT
19/20
Memory
30/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
Quality
qwen3-vl:2b
Reasoning
7/20
Coding
0/20
Instruction
11/20
Structured
7/15
Math
13/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong 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