Qwen3-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
91 vs 88
Hardware Fit
98 vs 86
Quality Score
88 vs 89
Hardware
Qwen3-30B:30b gemma4:12b-it-qat
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMac mini
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Apple M4 Pro
Cores2012
RAM55 GB24 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.28000macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
Qwen3-30B:30b gemma4:12b-it-qat
Tokens/sec80.530.0
First chunk158 ms686 ms
TTFT158 ms7.1 s
Load time21.8 s5.4 s
Memory usage20.3 GB7.1 GB
Memory %37%30%
HW Fit Score Breakdown
Qwen3-30B:30b
Speed
50/50
TTFT
20/20
Memory
28/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
Qwen3-30B:30b
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
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