openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Sep 29, 2026 · Apple M5 Max
qwen/qwen3.6-27b
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
Global Score
83 vs 76
Hardware Fit
80 vs 47
Quality Score
84 vs 89
Hardware
openai/gpt-oss-20b qwen/qwen3.6-27b
MachineMacBook ProGMKtec EVO-X3
CPUApple M5 MaxAMD RYZEN AI MAX+ 395
Cores1832
RAM128 GB120 GB
GPUApple M5 MaxAMD Radeon(TM) 8060S Graphics
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b qwen/qwen3.6-27b
Tokens/sec138.410.7
First chunk3 ms35 ms
TTFT30.0 s885 ms
Load time6.8 s127.6 s
Memory usage0.5 GB67.5 GB
Memory %0%56%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen/qwen3.6-27b
Speed
9/50
TTFT
16/20
Memory
22/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
12/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen/qwen3.6-27b
Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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