lmstudio-community/Phi-4-reasoning-plus-MLX-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
smollm2:360m
OLLAMA GGUFllama · 361.82M · F16
Mar 2, 2026 · Apple M4
Global Score
33 vs 52
Hardware Fit
74 vs 100
Quality Score
15 vs 32
Hardware
lmstudio-community… smollm2:360m
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
lmstudio-community… smollm2:360m
Tokens/sec11.5117.9
First chunk670 msN/A
TTFT670 ms43 ms
Load timeN/A0.4 s
Memory usage3.0 GB1.2 GB
Memory %9%4%
HW Fit Score Breakdown
lmstudio-community/Phi-…
Speed
24/50
TTFT
20/20
Memory
30/30
smollm2:360m
Speed
40/50
TTFT
30/20
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
smollm2:360m
Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
9/15
Math
4/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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