qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 19, 2026 · Apple M4 Max
lmstudio-community/Phi-4-reasoning-plus-MLX-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
89 vs 33
Hardware Fit
96 vs 74
Quality Score
86 vs 15
Hardware
qwen3-coder:30b lmstudio-community…
MachineMacBook ProMacBook Air
CPUApple M4 MaxApple M4
Cores1610
RAM64 GB32 GB
GPUApple M4 MaxApple M4
OSmacOS 26.5.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-coder:30b lmstudio-community…
Tokens/sec89.911.5
First chunk188 ms670 ms
TTFT188 ms670 ms
Load time4.0 sN/A
Memory usage30.2 GB3.0 GB
Memory %47%9%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
lmstudio-community/Phi-…
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
lmstudio-community/Phi-…
Reasoning
8/20
Coding
1/20
Instruction
1/20
Structured
1/15
Math
1/15
Multilingual
3/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Weak
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