lmstudio-community/Phi-4-reasoning-plus-MLX-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Global Score
33 vs 73
Hardware Fit
74 vs 93
Quality Score
15 vs 65
Hardware
lmstudio-community… lfm2.5:latest
MachineMacBook AirLENOVO 20L7CTO1WW
CPUApple M4Intel Core™ i5-8350U
Cores108
RAM32 GB23 GB
GPUApple M4Kaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.3Fedora Linux 44
Archarm64x64
Power Modebalancedperformance
Performance
lmstudio-community… lfm2.5:latest
Tokens/sec11.518.3
First chunk670 ms981 ms
TTFT670 ms981 ms
Load timeN/A8.0 s
Memory usage3.0 GB4.9 GB
Memory %9%21%
HW Fit Score Breakdown
lmstudio-community/Phi-…
Speed
24/50
TTFT
20/20
Memory
30/30
lfm2.5:latest
Speed
43/50
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
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate 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