lfm2.5:latest

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Good

Jun 11, 2026 · Intel Core™ i5-8350U

qwen3.5:latest

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Not Rec.

Mar 8, 2026 · Apple M4

Global Score

73 vs 34

Hardware Fit

93 vs 58

Quality Score

65 vs 23

Hardware

lfm2.5:latest qwen3.5:latest

MachineLENOVO 20L7CTO1WWMac mini

CPUIntel Core™ i5-8350UApple M4

Cores810

RAM23 GB16 GB

GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4

OSFedora Linux 44macOS 26.3

Archx64arm64

Power Modeperformancebalanced

Performance

lfm2.5:latest qwen3.5:latest

Tokens/sec18.313.3

First chunk981 ms438 ms

TTFT981 ms19.8 s

Load time8.0 s0.2 s

Memory usage4.9 GB8.0 GB

Memory %21%50%

HW Fit Score Breakdown

lfm2.5:latest

Speed

43/50

TTFT

20/20

Memory

30/30

qwen3.5:latest

Speed

32/50

TTFT

1/20

Memory

25/30

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

qwen3.5:latest

Reasoning

6/20

Coding

1/20

Instruction

3/20

Structured

0/15

Math

5/15

Multilingual

8/10

Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

View lfm2.5:latest details | View qwen3.5:latest details

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