Back to leaderboard

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

qwen3-coder:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Good

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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest