qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Apr 24, 2026 · AMD Ryzen 5 5500
Global Score
66 vs 90
Hardware Fit
91 vs 88
Quality Score
55 vs 91
Hardware
qwen3.8-27b-mlx openai/gpt-oss-20b
MachineMacBook ProASUS
CPUApple M5 MaxAMD Ryzen 5 5500
Cores1812
RAM64 GB31 GB
GPUApple M5 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 27.0Nobara Linux 43
Archarm64x64
Power Modebalancedperformance
Performance
qwen3.8-27b-mlx openai/gpt-oss-20b
Tokens/sec33.258.7
First chunk7 ms6 ms
TTFT311 ms4.5 s
Load timeN/AN/A
Memory usage0.5 GB11.9 GB
Memory %1%38%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
28/30
Quality
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
openai/gpt-oss-20b
Reasoning
18/20
Coding
15/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong 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