lmstudio-community/Phi-4-reasoning-plus-MLX-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen3:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
33 vs 86
Hardware Fit
74 vs 98
Quality Score
15 vs 81
Hardware
lmstudio-community… qwen3:30b
MachineMacBook AirASUS
CPUApple M4Intel Core™ Ultra 9 285K
Cores1024
RAM32 GB47 GB
GPUApple M4NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
lmstudio-community… qwen3:30b
Tokens/sec11.5204.8
First chunk670 ms96 ms
TTFT670 ms674 ms
Load timeN/A5.2 s
Memory usage3.0 GB20.5 GB
Memory %9%43%
HW Fit Score Breakdown
lmstudio-community/Phi-…
Speed
24/50
TTFT
20/20
Memory
30/30
qwen3:30b
Speed
50/50
TTFT
20/20
Memory
28/30
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
qwen3:30b
Reasoning
16/20
Coding
12/20
Instruction
17/20
Structured
12/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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