Qwen3-Coder-30B:30B
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Core™ Ultra X7 358H
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Jul 7, 2026 · Cortex-X925
Global Score
88 vs 94
Hardware Fit
91 vs 100
Quality Score
87 vs 92
Hardware
Qwen3-Coder-30B:30B gemma4:26b
MachineGMKtec NucBox EVO-T2SASUSTeK COMPUTER INC. GX10
CPUIntel Core™ Ultra X7 358HCortex-X925
Cores1620
RAM64 GB122 GB
GPUIntel(R) Arc(TM) B390 GPUDevice 2e12
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
Qwen3-Coder-30B:30B gemma4:26b
Tokens/sec32.267.4
First chunk540 ms529 ms
TTFT540 ms529 ms
Load time15.6 s6.0 s
Memory usage17.7 GB17.6 GB
Memory %28%15%
HW Fit Score Breakdown
Qwen3-Coder-30B:30B
Speed
41/50
TTFT
20/20
Memory
30/30
gemma4:26b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
Qwen3-Coder-30B:30B
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: Strong Multilingual: Strong
gemma4:26b
Reasoning
18/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
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