gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
Global Score
33 vs 92
Hardware Fit
50 vs 95
Quality Score
25 vs 90
Hardware
gemma4:26b qwen/qwen3-vl-30b
MachineMac miniASUS
CPUApple M4AMD Ryzen 5 5500
Cores1012
RAM24 GB31 GB
GPUApple M4Navi 44 [Radeon RX 9060 XT]
OSmacOS 26.3Nobara Linux 43
Archarm64x64
Power Modebalancedperformance
Performance
gemma4:26b qwen/qwen3-vl-30b
Tokens/sec20.024.8
First chunk941 ms11 ms
TTFT30.0 s735 ms
Load time0.2 s11.7 s
Memory usage20.3 GB0.6 GB
Memory %85%2%
HW Fit Score Breakdown
gemma4:26b
Speed
42/50
TTFT
0/20
Memory
8/30
qwen/qwen3-vl-30b
Speed
45/50
TTFT
20/20
Memory
30/30
Quality
gemma4:26b
Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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
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