lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
73 vs 74
Hardware Fit
93 vs 99
Quality Score
65 vs 63
Hardware
lfm2.5:latest llama3.2:3b
MachineLENOVO 20L7CTO1WWNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i5-8350UCortex-A78AE
Cores86
RAM23 GB7 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Integrated / Unknown
OSFedora Linux 44Ubuntu 22.04.5 LTS
Archx64arm64
Power Modeperformancebalanced
Performance
lfm2.5:latest llama3.2:3b
Tokens/sec18.321.1
First chunk981 ms1032 ms
TTFT981 ms1.0 s
Load time8.0 s8.4 s
Memory usage4.9 GB2.4 GB
Memory %21%32%
HW Fit Score Breakdown
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
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
llama3.2:3b
Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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