lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 22, 2026 · Apple M1 Pro
Global Score
73 vs 66
Hardware Fit
93 vs 100
Quality Score
65 vs 52
Hardware
lfm2.5:latest hf.co/empero-ai/Qw…
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M1 Pro
Cores810
RAM23 GB16 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M1 Pro
OSFedora Linux 44macOS 26.6.2
Archx64arm64
Power Modeperformancebalanced
Performance
lfm2.5:latest hf.co/empero-ai/Qw…
Tokens/sec18.340.2
First chunk981 ms325 ms
TTFT981 ms325 ms
Load time8.0 s3.1 s
Memory usage4.9 GB4.7 GB
Memory %21%30%
HW Fit Score Breakdown
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
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
hf.co/empero-ai/Qwen3.8…
Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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