hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16
OLLAMA GGUFqwen35 · 1.94B · BF16
Aug 22, 2026 · Apple M1 Pro
cogito:3b
OLLAMA GGUFllama · 3.6B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
66 vs 67
Hardware Fit
100 vs 100
Quality Score
52 vs 53
Hardware
hf.co/empero-ai/Qw… cogito:3b
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/empero-ai/Qw… cogito:3b
Tokens/sec40.245.6
First chunk325 ms177 ms
TTFT325 ms177 ms
Load time3.1 s0.8 s
Memory usage4.7 GB7.0 GB
Memory %30%22%
HW Fit Score Breakdown
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
cogito:3b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
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
cogito:3b
Reasoning
6/20
Coding
8/20
Instruction
13/20
Structured
15/15
Math
2/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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