lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
73 vs 78
Hardware Fit
93 vs 59
Quality Score
65 vs 86
Hardware
lfm2.5:latest GPT-20B:20b
MachineLENOVO 20L7CTO1WWGMKtec NucBox EVO-T2S
CPUIntel Core™ i5-8350UIntel Core™ Ultra X7 358H
Cores816
RAM23 GB64 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Intel(R) Arc(TM) B390 GPU
OSFedora Linux 44Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
lfm2.5:latest GPT-20B:20b
Tokens/sec18.319.6
First chunk981 ms2068 ms
TTFT981 ms9.9 s
Load time8.0 s12.8 s
Memory usage4.9 GB12.9 GB
Memory %21%20%
HW Fit Score Breakdown
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
GPT-20B:20b
Speed
26/50
TTFT
3/20
Memory
30/30
Quality
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
GPT-20B:20b
Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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