Qwen3-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
88 vs 91
Hardware Fit
91 vs 96
Quality Score
87 vs 89
Hardware
Qwen3-30B:30b gemma4:12b-mlx
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxMacBook Pro
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorApple M2 Pro
Cores3210
RAM31 GB16 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUApple M2 Pro
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
Qwen3-30B:30b gemma4:12b-mlx
Tokens/sec42.824.7
First chunk434 ms610 ms
TTFT434 ms610 ms
Load time19.9 s3.6 s
Memory usage17.9 GB7.1 GB
Memory %58%45%
HW Fit Score Breakdown
Qwen3-30B:30b
Speed
50/50
TTFT
20/20
Memory
21/30
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
Qwen3-30B: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
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
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