qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 19, 2026 · Apple M4 Max
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
89 vs 77
Hardware Fit
96 vs 74
Quality Score
86 vs 78
Hardware
qwen3-coder:30b phi4:14b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M4 MaxCortex-X925
Cores1620
RAM64 GB122 GB
GPUApple M4 MaxDevice 2e12
OSmacOS 26.5.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen3-coder:30b phi4:14b
Tokens/sec89.922.9
First chunk188 ms198 ms
TTFT188 ms198 ms
Load time4.0 s10.3 s
Memory usage30.2 GB14.7 GB
Memory %47%12%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
Quality
qwen3-coder:30b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
phi4:14b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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