Back to leaderboard

lfm2.5:latest

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Good

Jun 11, 2026 · Intel Core™ i5-8350U

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Marginal

Jun 26, 2026 · Cortex-A78AE

Global Score
73 vs 46
Hardware Fit
93 vs 61
Quality Score
65 vs 40

Hardware

lfm2.5:latest llama3.1:8b
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 llama3.1:8b
Tokens/sec18.37.8
First chunk981 ms1625 ms
TTFT981 ms1.6 s
Load time8.0 s21.8 s
Memory usage4.9 GB5.2 GB
Memory %21%71%

HW Fit Score Breakdown

lfm2.5:latest

Speed
43/50
TTFT
20/20
Memory
30/30

llama3.1:8b

Speed
26/50
TTFT
20/20
Memory
15/30

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

llama3.1:8b

Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest