qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
microllm-50m:latest
OLLAMA GGUFllama · 49.31M · F16
Jun 28, 2026 · Apple M4 Pro
Global Score
18 vs 28
Hardware Fit
53 vs 80
Quality Score
3 vs 5
Hardware
qwen3.5:0.8b microllm-50m:latest
MachineLENOVO 20L7CTO1WWMac mini
CPUIntel Core™ i5-8350UApple M4 Pro
Cores812
RAM23 GB24 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4 Pro
OSFedora Linux 43macOS 15.6.1
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:0.8b microllm-50m:latest
Tokens/sec9.41000000.0
First chunk799 ms50 ms
TTFT30.0 s30.0 s
Load time3.3 s0.3 s
Memory usage1.9 GB0.1 GB
Memory %8%1%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
23/50
TTFT
0/20
Memory
30/30
microllm-50m:latest
Speed
50/50
TTFT
0/20
Memory
30/30
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
microllm-50m:latest
Reasoning
0/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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