lmstudio-community/Phi-4-reasoning-plus-MLX-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Qwen3-Coder-30B:30B
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Core™ Ultra X7 358H
Global Score
33 vs 88
Hardware Fit
74 vs 91
Quality Score
15 vs 87
Hardware
lmstudio-community… Qwen3-Coder-30B:30B
MachineMacBook AirGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
lmstudio-community… Qwen3-Coder-30B:30B
Tokens/sec11.532.2
First chunk670 ms540 ms
TTFT670 ms540 ms
Load timeN/A15.6 s
Memory usage3.0 GB17.7 GB
Memory %9%28%
HW Fit Score Breakdown
lmstudio-community/Phi-…
Speed
24/50
TTFT
20/20
Memory
30/30
Qwen3-Coder-30B:30B
Speed
41/50
TTFT
20/20
Memory
30/30
Quality
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
Qwen3-Coder-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
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