qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 19, 2026 · Apple M4 Max
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
Global Score
80 vs 87
Hardware Fit
52 vs 79
Quality Score
92 vs 90
Hardware
qwen/qwen3.8-27b gpt-oss:20b
MachineMacBook ProMac mini
CPUApple M4 MaxApple M4
Cores1610
RAM128 GB24 GB
GPUApple M4 MaxApple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.8-27b gpt-oss:20b
Tokens/sec16.126.4
First chunk14 ms505 ms
TTFT5.8 s6.7 s
Load time8.5 s10.5 s
Memory usage0.0 GB13.1 GB
Memory %0%55%
HW Fit Score Breakdown
qwen/qwen3.8-27b
Speed
17/50
TTFT
5/20
Memory
30/30
gpt-oss:20b
Speed
50/50
TTFT
6/20
Memory
23/30
Quality
qwen/qwen3.8-27b
Reasoning
19/20
Coding
16/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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