qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Aug 18, 2026 · Apple M4 Max
dolphin-phi:2.7b
OLLAMA GGUFphi2 · 3B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
87 vs 61
Hardware Fit
83 vs 100
Quality Score
88 vs 44
Hardware
qwen/qwen3.8-27b dolphin-phi:2.7b
MachineMacBook ProMacBook Air
CPUApple M4 MaxApple M4
Cores1610
RAM128 GB32 GB
GPUApple M4 MaxApple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.8-27b dolphin-phi:2.7b
Tokens/sec29.156.1
First chunk9 msN/A
TTFT650 ms108 ms
Load timeN/A0.4 s
Memory usage21.0 GB2.2 GB
Memory %16%7%
HW Fit Score Breakdown
qwen/qwen3.8-27b
Speed
33/50
TTFT
20/20
Memory
30/30
dolphin-phi:2.7b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
qwen/qwen3.8-27b
Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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
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