dolphin-phi:2.7b
OLLAMA GGUFphi2 · 3B · Q4_0
Mar 1, 2026 · Apple M4
cogito:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
61 vs 77
Hardware Fit
100 vs 92
Quality Score
44 vs 70
Hardware
dolphin-phi:2.7b cogito:8b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
dolphin-phi:2.7b cogito:8b
Tokens/sec56.121.0
First chunkN/A312 ms
TTFT108 ms312 ms
Load time0.4 s0.8 s
Memory usage2.2 GB10.4 GB
Memory %7%33%
HW Fit Score Breakdown
dolphin-phi:2.7b
Speed
40/50
TTFT
30/20
Memory
30/30
cogito:8b
Speed
42/50
TTFT
20/20
Memory
30/30
Quality
dolphin-phi:2.7b
Reasoning
10/20
Coding
6/20
Instruction
12/20
Structured
2/15
Math
9/15
Multilingual
5/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Poor Math: Adequate Multilingual: Adequate
cogito:8b
Reasoning
14/20
Coding
13/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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