qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
92 vs 76
Hardware Fit
95 vs 51
Quality Score
90 vs 87
Hardware
qwen/qwen3-vl-30b qwen3-coder:latest
MachineASUSDell Inc. Inspiron 15 3530
CPUAMD Ryzen 5 5500Intel Gen Intel® Core™ i7-1355U
Cores1212
RAM31 GB31 GB
GPUNavi 44 [Radeon RX 9060 XT]Raptor Lake-P [Iris Xe Graphics]
OSNobara Linux 43cachyos rolling
Archx64x64
Power Modeperformancelow-power
Performance
qwen/qwen3-vl-30b qwen3-coder:latest
Tokens/sec24.87.6
First chunk11 ms2037 ms
TTFT735 ms2.0 s
Load time11.7 s8.7 s
Memory usage0.6 GB18.9 GB
Memory %2%61%
HW Fit Score Breakdown
qwen/qwen3-vl-30b
Speed
45/50
TTFT
20/20
Memory
30/30
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
Quality
qwen/qwen3-vl-30b
Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder:latest
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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