qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
92 vs 84
Hardware Fit
95 vs 82
Quality Score
90 vs 85
Hardware
qwen/qwen3-vl-30b gemma4:12b-mlx
MachineASUSMacBook Pro
CPUAMD Ryzen 5 5500Apple M2 Pro
Cores1210
RAM31 GB16 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M2 Pro
OSNobara Linux 43macOS 26.5
Archx64arm64
Power Modeperformancebalanced
Performance
qwen/qwen3-vl-30b gemma4:12b-mlx
Tokens/sec24.827.2
First chunk11 ms732 ms
TTFT735 ms8.1 s
Load time11.7 s3.5 s
Memory usage0.6 GB7.1 GB
Memory %2%44%
HW Fit Score Breakdown
qwen/qwen3-vl-30b
Speed
45/50
TTFT
20/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
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
gemma4:12b-mlx
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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