lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
73 vs 86
Hardware Fit
93 vs 78
Quality Score
65 vs 89
Hardware
lfm2.5:latest Kimi-48B:48B
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 Kimi-48B:48B
Tokens/sec18.322.8
First chunk981 ms721 ms
TTFT981 ms721 ms
Load time8.0 s23.0 s
Memory usage4.9 GB25.5 GB
Memory %21%40%
HW Fit Score Breakdown
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
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
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong 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