qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 18, 2026 · AMD Ryzen 5 5500U
mlx-community/gemma-3-4b-it-qat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
82 vs 80
Hardware Fit
71 vs 100
Quality Score
87 vs 71
Hardware
qwen3-coder:30b mlx-community/gemm…
MachineHP HP Pavilion Laptop 15-eh1xxxMacBook Air
CPUAMD Ryzen 5 5500UApple M4
Cores1210
RAM63 GB32 GB
GPUAMD Radeon(TM) GraphicsApple M4
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3-coder:30b mlx-community/gemm…
Tokens/sec14.343.2
First chunk869 ms428 ms
TTFT869 ms428 ms
Load time0.3 sN/A
Memory usage20.5 GB1.3 GB
Memory %32%4%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
22/50
TTFT
20/20
Memory
29/30
mlx-community/gemma-3-4…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3-coder: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
mlx-community/gemma-3-4…
Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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