qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
lfm2.5:8b
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
18 vs 80
Hardware Fit
53 vs 95
Quality Score
3 vs 73
Hardware
qwen3.5:0.8b lfm2.5:8b
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 43macOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:0.8b lfm2.5:8b
Tokens/sec9.498.5
First chunk799 ms167 ms
TTFT30.0 s2.5 s
Load time3.3 s3.0 s
Memory usage1.9 GB6.0 GB
Memory %8%37%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
23/50
TTFT
0/20
Memory
30/30
lfm2.5:8b
Speed
50/50
TTFT
17/20
Memory
28/30
Quality
qwen3.5:0.8b
Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
lfm2.5:8b
Reasoning
2/20
Coding
12/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate 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