phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Global Score
28 vs 73
Hardware Fit
66 vs 93
Quality Score
11 vs 65
Hardware
phi-1_5 lfm2.5:latest
MachineLENOVO 20BUS00700LENOVO 20L7CTO1WW
CPUIntel Core™ i5-5300UIntel Core™ i5-8350U
Cores48
RAM16 GB23 GB
GPUIntel(R) HD Graphics 5500Kaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 10 Professionnel 10.0.19045Fedora Linux 44
Archx64x64
Power Modebalancedperformance
Performance
phi-1_5 lfm2.5:latest
Tokens/sec6.918.3
First chunk3040 ms981 ms
TTFT3.0 s981 ms
Load timeN/A8.0 s
Memory usage1.4 GB4.9 GB
Memory %9%21%
HW Fit Score Breakdown
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
Quality
phi-1_5
Reasoning
2/20
Coding
2/20
Instruction
3/20
Structured
0/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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